Patent Application
20150106705
The present invention relates to teaching verb tense conventions in formal written language, and, more specifically, to an adaptive grammar teaching system configured to train users on identifying and correcting verb tense errors within natural language sentences.
Natural languages are spoken languages (such as American English), which have grammar rules governing the composition of the natural language. There are stylistic conventions that apply to the written form of a natural language, which, unlike natural language per se, must be taught. When a person has not learned the proper stylistic conventions for a written language, the student may encounter difficulty in communicating in writing, particularly in formal registers. For example, it may be particularly difficult for a person who does not understand the stylistic rules of American English to write an error-free research paper or formal letter, which limits that person's ability to communicate effectively through writing.
Grammar checkers, e.g., Grammerly.com, Thelma Thistleblossom, and grammar checkers included with document editors such as Microsoft Word, identify certain types of grammatical errors in written documents. However, grammar error identification/correction is not the same as teaching grammar rules or proper stylistic conventions, even when the grammar checker indicates why each identified error is an error. Grammar checkers generally do not teach either prescriptive or descriptive rules of grammar, nor do grammar checkers target particular problems that users have with grammatical or stylistic rules. At times, grammar checkers identify “errors” that are not errors at all, and rely on the user's knowledge to ultimately determine whether an error exists. Thus, grammar checkers are generally ineffective at teaching a user the conventions of formal written language.
Some English courses, e.g., in secondary and higher education, attempt to teach prescriptive grammar rules, largely using face-to-face teaching techniques, quizzes, and other activities. At times, automation is used in such traditional English courses. However, this automation generally consists of providing a student with multiple-choice questions and giving the student feedback on the student's selected answers. It can be difficult for an English teacher to identify and aid each student with the student's individual grammar or stylistic misconceptions, especially since classes tend to be large and students tend to have a wide range of skill gaps with respect to mastery of prescriptive grammar rules. At least the above mentioned deficiencies can allow students to complete English courses without learning all of the prescriptive grammar rules that they need to produce error-free communications.
Therefore, it would be beneficial to provide an automated grammar teaching system that is configured to teach concepts of prescriptive stylistic conventions that are targeted to the needs of students.
The approaches described in this section are approaches that could be pursued, but not necessarily approaches that have been previously conceived or pursued. Therefore, unless otherwise indicated, it should not be assumed that any of the approaches described in this section qualify as prior art merely by virtue of their inclusion in this section.
In the drawings:
In the following description, for the purposes of explanation, numerous specific details are set forth in order to provide a thorough understanding of the present invention. It will be apparent, however, that the present invention may be practiced without these specific details. In other instances, well-known structures and devices are shown in block diagram form in order to avoid unnecessarily obscuring the present invention.
An automated grammar teaching system delivers highly personalized, differentiated instruction to users. The automated grammar teaching system provides lessons and adaptive practice to build each student's skills for the rules of formal written English with respect to verb tense errors. Verb tense problems, configured to address each student's continuous learning needs with respect to granular grammar skills relating to identification and correction of verb tense errors, are automatically presented to students by the automated grammar teaching system.
According to an embodiment, the system displays a natural language sentence to a user, and allows the user to identify both the locations of verbs within the sentence and tenses of the identified verbs. The system reinforces correct designations of verbs and verb tenses using visual cues. In an embodiment, if a user incorrectly identifies one or more words as verbs within the displayed sentence, then the system displays remediation information to help the user understand the nature of the term that the user designated as a verb.
The system further allows the user to determine whether a displayed sentence includes a verb tense error and, if the sentence includes an error, to replace a particular verb in the sentence in order to correct the error. According to embodiments, the system also allows the user to select which verb in the displayed sentence to replace. The system further allows the user to obtain help in correcting a particular verb tense error by providing optional tasks that step the user through reasoning needed to correct the error.
Techniques are described hereafter for adaptively instructing a user on grammar rules governing verb tense.
Client device 110 may be implemented by any type of computing device that is communicatively connected to network 130. Example implementations of client device 110 include, without limitation, workstations, personal computers, laptop computers, personal digital assistants (PDAs), tablet computers, cellular telephony devices such as smart phones, and any other type of computing device.
In network arrangement 100, client device 110 is configured with a grammar client 112 and a browser 114 that displays a web page 116. Grammar client 112 may be implemented in any number of ways, including as a plug-in to browser 114, as an application running in connection with web page 116, as a stand-alone application running on client device 110, etc. Grammar client 112 may be implemented by one or more logical modules, and is described in further detail below. Browser 114 is configured to interpret and display web pages that are received over network 130 (e.g., web page 116), such as Hyper Text Markup Language (HTML) pages, and eXtensible Markup Language (XML) pages, etc. Client device 110 may be configured with other mechanisms, processes and functionalities, depending upon a particular implementation.
Further, client device 110 is communicatively coupled to a display device (not shown in
Network 130 may be implemented with any type of medium and/or mechanism that facilitates the exchange of information between client device 110 and server device 120. Furthermore, network 130 may facilitate use of any type of communications protocol, and may be secured or unsecured, depending upon the requirements of a particular embodiment.
Server device 120 may be implemented by any type of computing device that is capable of communicating with client device 110 over network 130. In network arrangement 100, server device 120 is configured with a grammar service 122, a verb correction service 124, a verb location service 126, and an optional tasks service 128. One or more of services 122-128 may be part of a cloud computing service. Functionality attributed to one or more of services 122-128 may be performed by a different service/client, such as another of services 122-128 or grammar client 112, according to embodiments. Services 122-128 may be implemented by one or more logical modules, and are described in further detail below. Server device 120 may be configured with other mechanisms, processes and functionalities, depending upon a particular implementation.
Server device 120 is communicatively coupled to database 140. Database 140 may reside in any type of storage, including volatile and non-volatile storage (e.g., random access memory (RAM), one or more hard or floppy disks, main memory, etc.), and may be implemented by one or more logical databases. The storage on which database 140 resides may be external or internal to server device 120.
Any of grammar client 112 and services 122-128 may receive and respond to Application Programming Interface (API) calls, Simple Object Access Protocol (SOAP) messages, requests via HyperText Transfer Protocol (HTTP), HyperText Transfer Protocol Secure (HTTPS), Simple Mail Transfer Protocol (SMTP), or any other kind of communication, e.g., from one of the other services 122-128 or grammar client 112. Further, any of grammar client 112 and services 122-128 may send one or more such communications over network 130, e.g., to one of the other entities of the system.
In an embodiment, each of the processes described in connection with one or more of grammar client 112 and services 122-128 are performed automatically and may be implemented using one or more computer programs, other software elements, and/or digital logic in any of a general-purpose computer or a special-purpose computer, while performing data retrieval, transformation, and storage operations that involve interacting with and transforming the physical state of memory of the computer.
Database 140 stores a plurality of sets of problem data. In an embodiment, a set of problem data corresponds to a verb tense problem that may be displayed to a user, e.g., at graphical user interface (GUI) 300 of
A particular verb tense problem includes at least one natural language sentence where one or more verbs in the natural language sentence are presented in an incorrect tense in the context of the natural language sentence. According to an embodiment, a verb (as the term is used herein) is a complete verb string comprising one or more natural language words that represent the verb. The following are example verb strings: “have walked”, “walks”, “is walking”, “walked”. Each of these verb strings includes one or more words that represent the verb communicated by the verb string. Herein, reference to a verb refers to the one or more words of the verb string for the verb. Furthermore, references herein to “words” and “sentences” refer to natural language words and natural language sentences, respectively.
A natural language sentence, i.e., of a particular verb tense problem stored at database 140, may also include one or more pseudoverbs. A pseudoverb is one or more words that may be confused with a verb, but that are not used as a verb within the context of the sentence in which the pseudoverb appears. For example, a particular verb tense problem includes the sentence: “He won the vote.” In this sentence, “won” is a verb and “vote” is a pseudoverb because the word “vote” may be used as a verb, but is not used as a verb (but as a noun) in the given sentence.
According to embodiments, a verb tense problem includes either (a) a single sentence (e.g., GUI 300), or (b) two or more sentences configured to be displayed together (e.g., GUI 600). A set of problem data also includes one or more of:
To illustrate a particular set of problem data, database 140 includes, in connection with the particular set of problem data, metadata embedded into the following marked-up sentence:
In [_pseudoverb]order[/_pseudoverb] to [_infinitiveVerb]pay[/_infinitiveVerb] my student [_pseudoverb]loans[/_pseudoverb] on [_pseudoverb]time[_pseudoverb], I [_verb]make[/_verb] a spreadsheet of my [_pseudoverb]expenses[/pseudoverb] each month, and I [_verb]use[/_verb] an online [_pseudoverb]banking[/_pseudoverb] [_pseudoverb]program[/_pseudoverb].
In connection with this marked-up sentence, database 140 also includes the following information for the identified verbs:
According to an embodiment, metadata for a sentence includes a tag that grammar service 122 uses for remediation information. Such remediation metadata identifies one or more words or phrases in a sentence that are not involved in a tense shift. For example, metadata in the marked-up sentence given above identifies the word “order” as a pseudoverb (i.e., “In [_pseudoverb] order[/_pseudoverb] to . . . ”). Grammar service 122 uses such metadata to identify particular remediation information to display to a user. For example, if a user identifies the pseudoverb “order” as a verb, then grammar service 122 uses the tag that marks that word to identify remediation text to display to the user in response to the user identifying the pseudoverb as a verb. Such remediation text may indicate as follows: “The word ‘order’ can be used as a verb, but is not used as a verb in this sentence.”
Grammar service 122 sends information for GUI 300 (such as information from database 140 for a particular verb tense problem to be displayed), via network 130, to grammar client 112. Grammar client 112 makes GUI 300 available to browser 114 executing on client device 110, and browser 114 displays GUI 300, i.e., as part of web page 116. According to another embodiment, grammar client 112 causes GUI 300 to be displayed outside of a browser, e.g., as part of a stand-alone application.
GUI 300 depicts a natural language sentence 302 that includes a verb tense error that is an incorrect tense shift involving the verbs “checked” and “goes”. A verb tense error that is an incorrect tense shift is a grammatical error in which two or more verbs within a sentence, the tenses of which should agree, have tenses that do not agree. Agreeing verb tenses are verb tenses that convey the same time frame. For example, “checked” is a past tense verb that conveys a past time frame. The tense of the verb “goes” should agree with the tense of “checked”, but instead is a present tense verb that conveys a present time frame (which is inconsistent with the past time frame of “checked”).
According to an embodiment, database 140 includes the following marked-up version of natural language sentence 302:
According to an embodiment, grammar service 122 displays GUI 300 with instructions 304 that instruct the user to identify the verbs in sentence 302. Thus, through GUI 300, the grammar teaching system allows a user to practice verb identification in the context of pre-formulated natural language sentences. Verb identification is a fundamental granular grammar skill that a user needs in order to properly apply grammatical rules governing verb tense.
According to embodiments, a user identifies a particular word of sentence 302 as a verb, e.g., by clicking on a portion of GUI 300 that depicts the particular word, or by tapping (via a touch-sensitive display) on the portion of GUI 300 that depicts the particular word, or by moving a cursor to the portion of GUI 300 that depicts the particular word and identifying the word at the location of the cursor with a particular key stroke (such as ‘enter’, or ‘e’), etc. Verb location service 126 receives, through GUI 300, such verb identification input that identifies one or more words of displayed natural language sentence 302 as a verb.
To illustrate, GUI 310 of
In response to determining that the word “checked” is a verb, verb location service 126 causes “checked” to be visually highlighted. An example of such a highlight is depicted in GUI 320 of
Once the user has received feedback on the previous word identification (i.e., of “checked”), the user has an opportunity to identify the remaining verb in sentence 302. As depicted at input 324 of GUI 320, the user identifies the word “submissions” as a verb. In response to receiving input 324, verb location service 126 determines whether the word “submissions” is identified as a verb within information for the displayed verb tense problem. Marked-up Sentence I has no special tagging on “submissions.” Therefore verb location service 126 determines that “submissions” is neither a verb nor a pseudoverb.
In response to determining that the word “submissions” is not a verb, verb location service 126 displays information about the word in the graphical user interface, such as is depicted in GUI 330 of
According to embodiments, verb location service 126 displays more detailed information about the word “submissions” than is depicted in information display 334. For example, more detailed information about “submissions” may indicate that the term is similar to the verb “submit”, but is in a noun form.
As a further example, grammar service 122 displays the following sentence from a verb tense problem: “Many students want to improve their writing skills, so they practice the steps of the writing process.” In data for the problem, the word “writing” is labeled as a pseudoverb. In response to a user incorrectly designating the word “writing” in the example sentence as a verb, verb location service 126 displays information that is specific to the term “writing” as used in the sentence. Specifically, example help text reads “The word ‘writing’ is sometimes a verb, but it's not being used as one here.” In this example, verb location service 126 provides the user with information to help the user understand that certain words (i.e., pseudoverbs), such as “writing”, may be used as one of several parts of speech (noun, verb, etc.) depending on the context of the word within the sentence.
After providing feedback to the user for the user's identification of “submissions” as a verb, the user has another opportunity to identify the remaining verb in sentence 302. As shown in GUI 330, the user selects the word “goes” via input 336. Upon receiving input 336, verb location service 126 determines whether the word “goes” is identified as a verb within information for the displayed verb tense problem. Marked-up Sentence I identifies “goes” as a verb.
In response to determining that the word “goes” is a verb, verb location service 126 causes “goes” to be visually highlighted, such as is depicted in GUI 340 of
According to an embodiment, verb location service 126 does not move on to another kind of question about sentence 302 (such as the question presented in GUI 400 of
According to an embodiment, grammar service 122 displays GUI 400 of
Verb correction service 124 receives, via dialog 410, an indication of which control of controls 412-416 that the user activates. In response to receiving this indication, verb correction service 124 determines whether the verb tense associated with the activated control is the correct verb tense for the indicated verb.
For example, verb correction service 124 receives an indication that the user activated control 416, corresponding to future tense, for the verb “checked”. Based on information for the displayed verb tense problem, verb correction service 124 determines that the verb “checked” is actually in the past tense. In response to determining that the user has incorrectly identified the tense of the verb “checked”, verb correction service 124 provides the user with feedback, such as a visual indication that the user has selected the wrong tense (e.g., outlining the verb string in red), displayed information about how to select the correct tense of a verb, etc.
As a further example, verb correction service 124 receives an indication that the user activated control 412, corresponding to past tense, for the verb “checked”. Based on information for the displayed verb tense problem, verb correction service 124 determines that the verb “checked” is in the past tense. In response to determining that the user has correctly identified the tense of the verb “checked”, verb correction service 124 provides the user with feedback, such as a visual indication that the user has selected the correct tense, automatically moving on to the next task for sentence 302 (thus, implicitly indicating that the user has selected the correct verb tense), changing the label on visual highlight 322 to “Past”, etc.
GUI 450 of
According to an embodiment, verb correction service 124 displays instructions 454 (GUI 450) that instruct the user to determine whether there is a tense shift error in displayed sentence 302. In connection with these instructions, verb correction service 124 causes dialog 460 to be displayed, which includes controls 462-466 by which the user may indicate one of the following: that there is a correct shift in verb tense (which is not a verb tense error), that there is an incorrect shift in verb tense (which is a verb tense error), or that there is no change in verb tense (which is not a verb tense error), respectively. In embodiments, any kind of verb tense error may be included in a dialog such as dialog 460.
Allowing a user to indicate whether there is a verb tense error, and more specifically, whether there is an incorrect or correct verb tense shift, allows the user an opportunity to apply the user's reasoning about the tenses of the verbs in the displayed sentence. The ability to recognize a verb tense error, including the ability to recognize the difference between a correct and incorrect verb tense shift, is another fundamental granular grammar skill that a user needs in order to properly apply grammatical rules governing verb tense.
Verb correction service 124 receives, via dialog 460, an indication of which control of controls 462-466 that the user activates. In response to receiving this indication, verb correction service 124 determines whether the user has correctly identified the error status of sentence 302, i.e., as indicated by one of controls 462-466. In the example of sentence 302, the sentence includes an incorrect tense shift verb tense error because the time frames indicated by the verbs “checked” and “goes” do not agree. As such, sentence 302 has an error status of “an incorrect shift in verb tense” corresponding to control 464.
If verb correction service 124 receives information indicating that the user has activated a control other than control 464, then verb correction service 124 determines that the user has selected an incorrect error status for sentence 302. In response to this determination, verb correction service 124 provides the user with feedback, such as a visual indication that the user has selected the wrong error status for sentence 302, information about how to correctly determine the error status of sentence 302, etc.
If verb correction service 124 receives information indicating that the user has activated control 464, “an incorrect shift in verb tense”, then verb correction service 124 determines that the user has selected the correct error status for sentence 302. In response to this determination, verb correction service 124 provides the user with an opportunity to correct the verb tense error, as described in connection with step 204 (of flowchart 200) below. This opportunity to correct the verb tense error implicitly communicates to the user that the user has selected the correct error status for sentence 302.
Returning to flowchart 200 of
By allowing a user to select which verb to change to correct an incorrect verb shift error in the displayed sentence, the system gives the user flexibility in deciding the sentence's final tense. Such flexibility mirrors the flexibility inherent when the user drafts an original sentence, when the user needs to be able to correctly identify the appropriate tenses for the verbs in the sentence being drafted.
Some sentences, such as sentence 302, include one or more explicit time frame terms that dictate the time frame for at least some of the verbs in the sentence. In example sentence 302, the term “always” indicates a verb time frame of timeless statement or fact. As such, according to the grammar rules of American English, both of the verbs in sentence 302 should be in the present tense, which mirrors the time frame of the term “always” in the sentence.
Because sentence 302 includes an explicit indication of a time frame for the sentence, the user should select and change the verb “checked” to be in the present tense, since selecting and changing the verb “goes” to be in the past tense would cause both verbs to not agree with the time frame explicitly set by the sentence. According to an embodiment, verb correction service 124 provides the user with the opportunity to select which verb that the user will correct in sentence 302 and, if the user selects “goes” to change, provides the user with feedback indicating that the sentence has an explicit time frame set by the term “always” and explains that the verb “checked” should be changed rather than “goes”. In this embodiment, verb correction service 124 may also highlight any terms in the displayed sentence that explicitly indicate time frame (i.e., “always” in sentence 302). As a further example of explicit time frame indicators, when a particular sentence includes reference to a published article, any reference to the content of the published article is present tense, e.g., “As Karl Marx says in Das Kapital, . . . ”.
According to another embodiment, if correction of a particular displayed sentence requires changing a particular verb of the two or more verbs identified in the sentence (as with sentence 302), then verb correction service 124 automatically selects the verb that must be corrected for correction. For example, verb correction service 124 automatically selects the verb “checked” in sentence 302 for the user to correct, without requiring the user to perform the selection. Thus, verb correction service 124 automatically displays a control that allows the user to specify a replacement for “checked”, as described in further detail below.
Many other sentences would allow the user to identify any verb within the sentence for correction. For example, if sentence 302 read as follows, then the user may select either of “checked” or “goes” for correction: “I checked my assignment submissions to make sure the attachment goes through.” Since there is no explicit indication of time frame in this version of the sentence, the user is not restricted as to which verb the user should choose to correct.
At step 206 of flowchart 200, in response to receiving the selection input, a control that allows a user to specify a replacement for the particular verb in the natural language sentence is provided. For example, in response to the user selecting the verb “checked”, i.e., via input 472, verb correction service 124 causes control 482 to replace the depiction of the verb “checked” as shown in GUI 480 of
Further, in the example of GUI 480, control 482 is labeled with label 486, which depicts the verb that the user has chosen to replace (i.e., “checked”). Label 486 is styled to communicate that the label depicts the verb to be replaced, and to communicate that the label is not a hint as to what the verb should be replaced with. Specifically, label 486 is grayed out and also crossed out. Other styling may be used to set label 486 apart from other communications in GUI 480.
Verb correction service 124 receives, via control 482, a replacement string from the user that represents one or more words that the user would like to replace the selected verb. For example, a user types a string such as “checking”, “monitor”, or “check” into control 482.
At step 208, it is determined whether the replacement is included in a set of one or more verb corrections for the particular verb in information that is maintained for the natural language sentence. For example, verb correction service 124 determines whether the replacement string that the user provided via control 482 represents a verb correction in a set of one or more accurate verb corrections for the verb “checked” in data for the displayed problem (i.e., from database 140). In an embodiment, there is only one verb correction that is indicated as accurate for the particular verb in information maintained for sentence 302 in database 140.
To illustrate, if the user inputs the string “checking” via control 482, verb correction service 124 determines whether “checking” is one of the accurate corrections for the verb “checked” in sentence 302. In this example, the set of accurate corrections for the verb “checked” in data for sentence 302 includes only the correction “check”. As such, verb correction service 124 determines that the replacement string “checking” is not included in the set of verb corrections for the verb “checked”. In response to this determination, verb correction service 124 provides the user with feedback, such as a visual indication that the user has input an inaccurate correction for the verb “checked”, information about how to accurately correct the tense of the verb, etc.
As a further illustration, if the user inputs the string “monitor” via control 482, verb correction service 124 determines that the replacement string “monitor” is not an accurate correction of the verb “checked”, since “monitor” is not included in the set of accurate corrections for “checked”. According to an embodiment, verb correction service 124 further determines that “monitor” is not a form of the verb that the user is tasked with replacing, i.e., to check. In this embodiment, in addition to providing feedback indicating that the user has not accurately corrected sentence 302 (as indicated above), verb correction service 124 also provides feedback indicating that the user should provide a replacement string that is a form of the same verb as the verb being replaced.
As yet a further illustration, the user inputs the string “check” via control 482. When verb correction service 124 receives this replacement string, verb correction service 124 determines whether “check” is one of the accurate corrections for the verb “checked” in sentence 302. Since the set of accurate corrections for the verb “checked” includes the correction “check”, verb correction service 124 determines that the user has accurately corrected the tense of the verb “checked” in sentence 302.
At step 210, in response to determining that the replacement is included in the set of one or more verb corrections for the particular verb, one or more of the following are performed: communicate successful sentence correction to the user, and record information indicating successful sentence correction of the natural language sentence. For example, in response to determining that “check” is an accurate correction of the verb “checked” in sentence 302, verb correction service 124 communicates successful sentence correction to the user, an example of which is depicted in GUI 490 of
GUI 490 includes a depiction 492 of the replacement string provided by the user in the place where the verb “checked” used to be depicted within sentence 302. Further, depiction 492 is depicted with font features that distinguish depiction 492 from the rest of the words in sentence 302 (i.e., depiction 492 is black and bolded, where the rest of the words in sentence 302 are not bolded and are grayed out). Such a depiction of the replacement string implicitly communicates to the user that the user has input an accurate correction of the verb tense of “checked”. Also, GUI 490 includes icon 494, which is a green check mark. Icon 494 is an explicit indication of a correct answer to the question of verb tense correction.
According to an embodiment, in response to determining that the user has accurately corrected the tense of the verb “checked” in sentence 302, verb correction service 124 records information indicating the successful correction. For example, instead of or in addition to communicating successful sentence correction to the user, verb correction service 124 records information, e.g., in database 140, that the user has successfully corrected the incorrect verb tense shift error in sentence 302. Such information may be used to aid in selection of verb tense problems to display to the user in the future, to create a summary of the user's progress, etc.
According to an embodiment, at least some of the verb tense problems in database 140 include data for multiple sentences that are configured to be presented all together to a user, i.e., in paragraph form.
At step 502 of flowchart 500, a graphical user interface that depicts two or more natural language sentences is displayed at a computing device, wherein at least a first natural language sentence of the two or more natural language sentences includes a verb tense error involving a particular verb within the first natural language sentence. For example, GUI 600 of
At step 504, information indicating that the first natural language sentence includes a verb tense error is received from a user. For example, verb correction service 124 displays dialog 610 that instructs the user to choose the correct description of verb string 608. Dialog 610 further includes a control 612 that corresponds to the input “verb error” and a control 614 that corresponds to the input “no error”. The inputs assigned to controls 612 and 614 are illustrative and non-limiting within embodiments. Verb correction service 124 receives information indicating that the user has activated one of controls 612 and 614, which informs verb correction service 124 that the user has designated verb string 608 to be in error, or to be not in error, respectively.
According to an example, the user activates control 612. Verb correction service 124 receives information indicating that the user has activated control 612, by which the user indicates that sentence 602 includes a verb tense error at verb string 608.
At step 506, in response to receiving, from the user, the information indicating that the first natural language sentence includes a verb tense error, a control is provided that allows the user to input information for a corrected verb to replace the particular verb in the first natural language sentence. For example, verb correction service 124 receives information, via dialog 610, indicating that the user has activated control 612, which informs verb correction service 124 that the user has designated verb string 608 to be in error. In response to receiving this information, verb correction service 124 replaces the depiction of the verb string “have identify” in sentence 602 with control 622, as depicted in GUI 620 of
Within embodiments, control 622 allows the user to specify a replacement for a verb in any manner, including allowing selection of a replacement from a list, using speech recognition technology to allow the user to speak a replacement for the verb, allowing a user to type in a verb correction string, etc. Furthermore, control 622 is labeled by label 624, which indicates to the user that control 622 replaced the verb string “have identify”, indicated in label 624. Label 624 is displayed using font style elements that communicate to the user that the label represents the phrase being replaced and is not a hint, i.e., the lettering of label 624 is grayed out and also struck through.
At step 508, input information that represents a particular verb correction is received via the control. For example, verb correction service 124 receives the string “have identified” via control 622. The received string is a verb correction string that a user has input via control 622.
At step 510, it is determined whether the particular verb correction is included in a set of one or more verb corrections for the particular verb in information that is maintained for the first natural language sentence. For example, verb correction service 124 determines whether the verb correction string “have identified” is included in a set of verb corrections for the original verb string “have identify” (of sentence 602) in information for the verb tense problem, i.e., from database 140. Verb correction service 124 determines that the set of verb corrections for “have identify” in data for sentence 602 includes the phrase “have identified”. As such, verb correction service 124 determines that “have identified” is an accurate correction of the verb string “have identify” in sentence 602.
At step 512, in response to determining that the corrected verb is included in the set of one or more verb corrections for the particular verb, one or more of the following are performed: communicating successful sentence correction to the user, and recording information indicating successful sentence correction of the first natural language sentence.
According to an embodiment, in response to determining that the verb correction string “have identified” is in the set of verb corrections for the original verb string “have identify” of sentence 602, verb correction service 124 communicates successful sentence correction to the user. For example, GUI 630 of
Also, GUI 630 displays a mechanism to analyze the subsequent sentence 604, which also implicitly indicates to the user that the user has input an accurate correction of the verb string in sentence 602. According to embodiments, communication of successful sentence correction to a user may be accomplished in any manner, including displaying a message that states that the user's answer is correct, playing a sound that indicates that the user is correct, etc.
According to an embodiment, in response to determining that the corrected verb string represents an accurate correction of the verb string “have identify” in sentence 602, verb correction service 124 records information indicating successful sentence correction of sentence 602. For example, instead of or in addition to communicating successful sentence correction to the user, verb correction service 124 records information, e.g., in database 140, that the user has successfully corrected the verb tense error in sentence 602. Such information may be used to aid in selection of verb tense problems to display to the user in the future, or to create a summary of the user's progress, etc.
According to an embodiment, if the verb correction string, input via control 622 of GUI 620, is not in the set of accurate corrections for the indicated verb, then verb correction service 124 provides feedback to the user regarding the inaccurate verb correction string. For example, as depicted in GUI 640 of
In response to determining that the input verb correction string is not an accurate correction of “have identify” in sentence 602, verb correction service 124 provides feedback, such as one or more visual cues that the input correction string is inaccurate, e.g., displaying an icon, depicting the verb correction string with a particular style of font, displaying a visual indicator integrated with control 622 such as outlining control 622 in a particular color, etc.
Furthermore, the feedback may include information about the verb correction string, i.e., at information box 642. According to the embodiment depicted in GUI 640, information box 642 includes information about how to formulate an accurate correction of “have identify” in natural language sentence 602. Information box 642 includes information that is specific to the verb correction string “has identified”, and may include information such as an acknowledgement that the verb correction string is a tense of the given verb. Verb correction service 124 retrieves the verb-specific information for information box 642 from (or based on) data for the displayed verb tense problem.
According to an embodiment, verb correction service 124 determines that a verb correction string (such as “has identified”) is in the correct tense, but does not agree with the plurality of the subject of the sentence (“Alberto and Natalie”). As such, verb correction service 124 provides feedback to the user that instructs the user about agreement between the verb form and the subject of the sentence. In the example of GUI 640, verb correction service 124 provides the user with information stating that the verb correction string input by the user is in the correct tense, but should agree with the third-person plural subject (“Alberto and Natalie”). As such, verb correction service 124 provides sentence-specific feedback regarding number agreement between the subject and the verb.
As a further example, the user inputs “to identify” into control 622. Verb correction service 124 determines that “to identify” is not an accurate correction of “have identify” in sentence 602 because “to identify” is not in the set of accurate corrections for the verb. In response to determining that “to identify” is not an accurate correction of the indicated verb, verb correction service 124 provides feedback to the user as described above.
In the example feedback depicted in GUI 650 of
According to an embodiment, if verb correction service 124 determines that a verb correction string input by the user represents a version of the verb that is never correct, then verb correction service 124 provides the user with feedback that is specific to the error that the user committed. For example, the verb that the user is attempting to correct is “to write” and the user provides the verb correction string “have wrote” (which is a form of “to write” that is never correct). When verb correction service 124 receives this verb correction string, verb correction service 124 determines that the verb correction string “have wrote” is always erroneous based on one or more of data maintained for the verb in connection with the displayed verb tense problem, data maintained for the verb in a verb database within database 140, etc. From the data maintained for the verb, verb correction service 124 retrieves information to display to the user as feedback for this erroneous form of the verb. Such information provides feedback to teach the user that the form of the verb input by the user is never correct, and may also include proper alternatives to the incorrect form.
As depicted in GUI 630 of
According to an embodiment, verb correction service 124 automatically highlights and initiates questions about particular verb strings in a set of multiple displayed sentences in a predetermined order. For example, the data for a displayed problem indicates that a particular verb in each displayed sentence, in turn, should be highlighted. When each verb is highlighted, verb correction service 124 also displays a mechanism whereby the user may indicate whether the verb has a verb tense error as described above.
According to an embodiment, at least one of the displayed multiple sentences does not include a verb tense error. In this embodiment, verb correction service 124 automatically highlights a verb string in a displayed sentence that does not include a verb tense error and displays a mechanism whereby the user may indicate whether the highlighted verb has a verb tense error. Verb correction service 124 automatically moves on to any remaining verb strings to be highlighted in response to the user indicating that the verb string does not have a verb tense error.
According to an embodiment depicted in GUI 660 of
According to an embodiment, grammar service 122 provides a set of optional tasks to guide a user through identifying an accurate correction for a particular verb tense error. The optional tasks step the user through the reasoning needed to identify an accurate correction, and provide details and help that are specific to the verb string and sentence in question.
A user is not required to complete the optional tasks associated with a particular verb tense problem in order to complete the problem. As such, a user may apply skills and intuition to problems presented to the user in a way that is most natural to the user, without unnecessarily performing the steps presented in the optional tasks. Nevertheless, if a user is having trouble reasoning through the steps needed to complete a problem, the user may engage the optional tasks to provide needed details. At any point in the optional tasks, the user may input a verb correction into the provided control.
According to an embodiment, if a user has not completed the optional tasks for a particular problem and the user provides an incorrect answer for the problem, then verb correction service 124 provides feedback to the user suggesting that the user complete the optional tasks for the problem, in addition to or instead of any other feedback. However, if the user gives an incorrect answer and has already completed the optional tasks for the problem in question, feedback for the incorrect answer does not include a suggestion to complete the optional tasks.
GUI 700 of
Returning to the example of GUI 700, in response to detecting that the user has selected option control 716, optional tasks service 128 populates subpanel 714 with controls 718 that allow the user to designate a description of a time frame of the action being performed in the verb string that the user is currently attempting to correct (i.e., “have identify” in sentence 602). Each of controls 718 corresponds to a distinct time frame for the action being performed in sentence 602.
If the user activates a control of controls 718 that does not accurately describe the time frame of the verb string or of the sentence in question (i.e., “have identify” in sentence 602), then optional tasks service 128 communicates to the user that the user has selected the wrong control, e.g., using a visual indicator (such as a red outline of the incorrectly selected control, an icon, etc.), text that gives information that includes that the incorrect control was selected, a sound that communicates that the selected control is incorrect, etc. According to an embodiment, text that optional tasks service 128 displays includes information about how to pick the correct time frame. Subsequently, the user is allowed to activate another control of controls 718 to continue the attempt to select the correct time frame for the verb string in question.
If the user activates a control of controls 718 that accurately describes the time frame of the verb string in question, then optional tasks service 128 communicates to the user that the user has selected a correct control of controls 718. For example, optional tasks service 128 displays a visual indicator of success, plays a sound that indicates success, implicitly indicates the user's success, etc. For example, optional tasks service 128 populates further subpanels in optional tasks side panel 710, as depicted in GUI 720 of
Specifically, GUI 720 depicts user selection of a control, of controls 718, that corresponds to “began in the past and continues or is recently completed”, which accurately describes the action of the verb string of sentence 602 that the user is currently attempting to correct. In response to determining that the user has selected the correct control of controls 718, optional tasks service 128 populates subpanel 722 with information indicating the name of the verb tense that should be used with the time frame that characterizes the action of the verb string to be corrected. This information allows the user to become familiar with the names of the tenses being taught. Furthermore, if the user is already familiar with the names of verb tenses, presentation of the name of the correct verb tense may be sufficient information for the user to complete correction of the verb string without completing further optional tasks.
In response to determining that the user has selected the correct control of controls 718, optional tasks service 128 also populates subpanel 724 with controls 726, which are three options for forming the verb tense needed to correct the verb string in question (i.e., “have identify” of sentence 602). The information presented in subpanel 724 may be considered a multiple choice question, and, according to an embodiment, the distractors for this multiple choice question are identified as described in further detail below.
According to embodiments, if optional tasks service 128 detects that the user has selected a particular control, of controls 726, that is not the correct way to formulate a verb of the given tense, then optional tasks service 128 communicates to the user that the selected control is incorrect in any manner as described herein, including by providing details about how to correctly formulate the given verb tense, automatically displaying hint information for the step of the optional tasks corresponding to subpanel 724, etc. If optional tasks service 128 detects that the user has selected a particular control, of controls 726, that is the correct way to formulate a verb of the given tense, then optional tasks service 128 communicates to the user that the selected control is correct in any manner as described herein.
At any point in the optional tasks, the user may request a hint about the current optional task, e.g., by activating hint button 728. Further, hint information is available for each step in solving any verb tense problem as described herein by activating hint button 728. According to an embodiment, when a user makes a mistake in connection with a verb tense problem or optional tasks, grammar service 122 visually highlights hint button 728 to remind the user that this hint option is available.
Once the user has successfully corrected the current verb string in question, grammar service 122 automatically moves on to any other verb strings of the currently displayed problem that the user has not yet corrected. At that point, the subpanels of optional tasks side panel 710 clear out and option control 716 is deselected in preparation for providing optional tasks that are specific to the next verb string in question.
According to an embodiment, incorrect verb tenses within verb tense problems in database 140 are formulated based, at least in part, on analysis of a corpus of information that indicate actual errors that are made by students. Analysis of such a corpus identifies common errors for particular verb tense situations. For example, such analysis indicates that, when a particular verb string should be in the past tense (e.g., “chose”), students tend to erroneously use one of: present tense (“choose”); present progressive tense (“is choosing”); present passive tense (“is chosen”); or past participle alone (“chosen”).
Thus, if a particular natural language sentence in a verb tense problem should have a past tense verb, the verb in the proper tense is replaced with an erroneous verb string, where the erroneous verb string is either one of the valid verb forms that students commonly misuse in the situation, or one of the malformed verb strings that students commonly produce. In the context of the example above, a verb string in the past tense is replaced, e.g., with the present passive form of the verb.
Similarly, multiple choice verb tense problems in database 140 include distractors that are based on verb tenses that students tend to erroneously use, as identified by analysis of the corpus of information described above. A distractor of a multiple choice problem is a plausible, but incorrect, option for the multiple-choice answer. In an embodiment, database 140 includes a list of common mistakes for formulating a particular verb tense. When grammar service 122 displays a multiple choice problem to a user, grammar service 122 determines the verb tense being tested by the question and automatically formulates distractors for the multiple choice question based on one or more of the list of common mistakes for the particular verb tense. Thus if the erroneous sentence is, “The Great Depression is beginning in 1929,” then the multiple choice list presented to the student might include the distractors “is begun” (present passive tense), “begins” (present tense), and “begun” (past participle alone) along with the correct answer “began” (past tense).
According to one embodiment, the techniques described herein are implemented by one or more special-purpose computing devices. The special-purpose computing devices may be hard-wired to perform the techniques, or may include digital electronic devices such as one or more application-specific integrated circuits (ASICs) or field programmable gate arrays (FPGAs) that are persistently programmed to perform the techniques, or may include one or more general purpose hardware processors programmed to perform the techniques pursuant to program instructions in firmware, memory, other storage, or a combination. Such special-purpose computing devices may also combine custom hard-wired logic, ASICs, or FPGAs with custom programming to accomplish the techniques. The special-purpose computing devices may be desktop computer systems, portable computer systems, handheld devices, networking devices or any other device that incorporates hard-wired and/or program logic to implement the techniques.
For example,
Computer system 800 also includes a main memory 806, such as a random access memory (RAM) or other dynamic storage device, coupled to bus 802 for storing information and instructions to be executed by processor 804. Main memory 806 also may be used for storing temporary variables or other intermediate information during execution of instructions to be executed by processor 804. Such instructions, when stored in non-transitory storage media accessible to processor 804, render computer system 800 into a special-purpose machine that is customized to perform the operations specified in the instructions.
Computer system 800 further includes a read only memory (ROM) 808 or other static storage device coupled to bus 802 for storing static information and instructions for processor 804. A storage device 810, such as a magnetic disk, optical disk, or solid-state drive is provided and coupled to bus 802 for storing information and instructions.
Computer system 800 may be coupled via bus 802 to a display 812, such as a cathode ray tube (CRT), for displaying information to a computer user. An input device 814, including alphanumeric and other keys, is coupled to bus 802 for communicating information and command selections to processor 804. Another type of user input device is cursor control 816, such as a mouse, a trackball, or cursor direction keys for communicating direction information and command selections to processor 804 and for controlling cursor movement on display 812. This input device typically has two degrees of freedom in two axes, a first axis (e.g., x) and a second axis (e.g., y), that allows the device to specify positions in a plane.
Computer system 800 may implement the techniques described herein using customized hard-wired logic, one or more ASICs or FPGAs, firmware and/or program logic which in combination with the computer system causes or programs computer system 800 to be a special-purpose machine. According to one embodiment, the techniques herein are performed by computer system 800 in response to processor 804 executing one or more sequences of one or more instructions contained in main memory 806. Such instructions may be read into main memory 806 from another storage medium, such as storage device 810. Execution of the sequences of instructions contained in main memory 806 causes processor 804 to perform the process steps described herein. In alternative embodiments, hard-wired circuitry may be used in place of or in combination with software instructions.
The term “storage media” as used herein refers to any non-transitory media that store data and/or instructions that cause a machine to operate in a specific fashion. Such storage media may comprise non-volatile media and/or volatile media. Non-volatile media includes, for example, optical disks, magnetic disks, or solid-state drives, such as storage device 810. Volatile media includes dynamic memory, such as main memory 806. Common forms of storage media include, for example, a floppy disk, a flexible disk, hard disk, solid-state drive, magnetic tape, or any other magnetic data storage medium, a CD-ROM, any other optical data storage medium, any physical medium with patterns of holes, a RAM, a PROM, and EPROM, a FLASH-EPROM, NVRAM, any other memory chip or cartridge.
Storage media are distinct from but may be used in conjunction with transmission media. Transmission media participate in transferring information between storage media. For example, transmission media include coaxial cables, copper wire and fiber optics, including the wires that comprise bus 802. Transmission media can also take the form of acoustic or light waves, such as those generated during radio-wave and infra-red data communications.
Various forms of media may be involved in carrying one or more sequences of one or more instructions to processor 804 for execution. For example, the instructions may initially be carried on a magnetic disk or solid-state drive of a remote computer. The remote computer can load the instructions into its dynamic memory and send the instructions over a telephone line using a modem. A modem local to computer system 800 can receive the data on the telephone line and use an infra-red transmitter to convert the data to an infra-red signal. An infra-red detector can receive the data carried in the infra-red signal and appropriate circuitry can place the data on bus 802. Bus 802 carries the data to main memory 806, from which processor 804 retrieves and executes the instructions. The instructions received by main memory 806 may optionally be stored on storage device 810 either before or after execution by processor 804.
Computer system 800 also includes a communication interface 818 coupled to bus 802. Communication interface 818 provides a two-way data communication coupling to a network link 820 that is connected to a local network 822. For example, communication interface 818 may be an integrated services digital network (ISDN) card, cable modem, satellite modem, or a modem to provide a data communication connection to a corresponding type of telephone line. As another example, communication interface 818 may be a local area network (LAN) card to provide a data communication connection to a compatible LAN. Wireless links may also be implemented. In any such implementation, communication interface 818 sends and receives electrical, electromagnetic or optical signals that carry digital data streams representing various types of information.
Network link 820 typically provides data communication through one or more networks to other data devices. For example, network link 820 may provide a connection through local network 822 to a host computer 824 or to data equipment operated by an Internet Service Provider (ISP) 826. ISP 826 in turn provides data communication services through the world wide packet data communication network now commonly referred to as the “Internet” 828. Local network 822 and Internet 828 both use electrical, electromagnetic or optical signals that carry digital data streams. The signals through the various networks and the signals on network link 820 and through communication interface 818, which carry the digital data to and from computer system 800, are example forms of transmission media.
Computer system 800 can send messages and receive data, including program code, through the network(s), network link 820 and communication interface 818. In the Internet example, a server 830 might transmit a requested code for an application program through Internet 828, ISP 826, local network 822 and communication interface 818.
The received code may be executed by processor 804 as it is received, and/or stored in storage device 810, or other non-volatile storage for later execution.
In the foregoing specification, embodiments of the invention have been described with reference to numerous specific details that may vary from implementation to implementation. The specification and drawings are, accordingly, to be regarded in an illustrative rather than a restrictive sense. The sole and exclusive indicator of the scope of the invention, and what is intended by the applicants to be the scope of the invention, is the literal and equivalent scope of the set of claims that issue from this application, in the specific form in which such claims issue, including any subsequent correction.
Given the interaction design, a model is built that describes in machine-readable fashion what the various components in the system, the properties that they have, and the values that those properties can take. A fragment of this model, in textual form, might look like this:
Type: TENSE_SHIFT_PROBLEM: The problem type where students are dealing with verb tenses which agree or disagree.
Properties:
Properties:
Values:
current-time (VERB_TIME):
number (PLURALITY):
past-participle (STRING):
past-perfect (STRING):
past-tense (STRING):
past-tense-generic (STRING):
plain-form (STRING):
possible-corrections (LIST<STRING>):
present-participle (STRING):
Selected Properties:
In parallel with the domain authoring activity, subject matter experts (SMEs) write and encode a set of paragraphs (for one problem type) and sentences (for the other problem type), some of which contain the kinds of verb tense errors that students tend to make and all of which employ verb tenses students are known to struggle with. Based on research, the common student errors can be grouped into two categories:
1. Malformations:
2. Inappropriate tense choices:
An example of a single sentence problem is:
These problem scenarios are then converted into problem templates in an existing problem generation infrastructure. In the multiple-sentence problems, individual problem instances are created by selecting a subset of the paragraph written by the SME. A function finds and fills in other basic tenses of each verb, based on the verb's plain form supplied by the SME. Another function surrounds key words and phrases in the sentence with tags as to the type of each word or phrase. When this conversion has been completed for the first sentence above, it looks like this:
and the verbs look like this:
This problem generation infrastructure then outputs XML files that represent each problem instance in terms of the domain model previously described.
This application claims the benefit of Provisional Appln. 61/890,875, filed Oct. 15, 2013, the entire contents of which is hereby incorporated by reference as if fully set forth herein, under 35 U.S.C. §119(e). This application is also related to application Ser. No. 13/875,107, titled “Multi-Layered Cognitive Tutor”, filed May 1, 2013, and to application Ser. No. 14/053,519, titled “Adaptive Grammar Instruction”, filed Oct. 14, 2013, the entire contents of each of which is hereby incorporated by reference as if fully set forth herein.
| Number | Date | Country | |
|---|---|---|---|
| 61890875 | Oct 2013 | US |
