Patent Application
20160328381
Embodiments of the present invention relate generally to natural language generation technologies and, more particularly, relate to a method, apparatus, and computer program product for referring expression generation.
In some examples, a natural language generation (NLG) system is configured to transform raw input data that is expressed in a non-linguistic format into a format that can be expressed linguistically, such as through the use of natural language. For example, raw input data may take the form of a value of a stock market index over time and, as such, the raw input data may include data that is suggestive of a time, a duration, a value and/or the like. Therefore, an NLG system may be configured to input the raw input data and output text that linguistically describes the value of the stock market index; for example, “Securities markets rose steadily through most of the morning, before sliding downhill late in the day.”
Data that is input into a NLG system may be provided in, for example, a recurrent formal structure. The recurrent formal structure may comprise a plurality of individual fields and defined relationships between the plurality of individual fields. For example, the input data may be contained in a spreadsheet or database, presented in a tabulated log message or other defined structure, encoded in a ‘knowledge representation’ such as the resource description framework (RDF) triples that make up the Semantic Web and/or the like. In some examples, the data may include numerical content, symbolic content or the like. Symbolic content may include, but is not limited to, alphanumeric and other non-numeric character sequences in any character encoding, used to represent arbitrary elements of information. In some examples, the output of the NLG system is text in a natural language (e.g. English, Japanese or Swahili), but may also be in the form of synthesized speech.
Methods, apparatuses, and computer program products are described herein that are configured to perform referring expression generation. In some example embodiments, a method is provided that comprises identifying an intended referent to be referred to in a textual output. The method of this embodiment may also include determining a lowest common ancestor for the intended referent and a previously referred-to entity within a part-of hierarchy. The method of this embodiment may also include determining that a salient ancestor of the intended referent is lower in the part-of hierarchy than the lowest common ancestor in an instance in which the intended referent is marked as not salient. The method of this embodiment may also include causing the salient ancestor to be set as a current target referent and a new salient ancestor to be determined for the current target referent. In some example embodiments, the default descriptor of each current target referent is added to the referring noun phrase and the part-of hierarchy is traversed via salient ancestor links until the new salient ancestor of the current target referent is higher than or equal to the lowest common ancestor.
Having thus described embodiments of the invention in general terms, reference will now be made to the accompanying drawings, which are not necessarily drawn to scale, and wherein:
Example embodiments will now be described more fully hereinafter with reference to the accompanying drawings, in which some, but not all, embodiments are shown. Indeed, the embodiments may take many different forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided so that this disclosure will satisfy applicable legal requirements. Like reference numerals refer to like elements throughout. The terms “data,” “content,” “information,” and similar terms may be used interchangeably, according to some example embodiments, to refer to data capable of being transmitted, received, operated on, and/or stored. Moreover, the term “exemplary”, as may be used herein, is not provided to convey any qualitative assessment, but instead merely to convey an illustration of an example. Thus, use of any such terms should not be taken to limit the spirit and scope of embodiments of the present invention.
Natural language texts that describe one or more entities, such as those entities that have a complex internal structure (e.g. machine parts, geographic locations, equipment or the like), include a number of assets (e.g. listing of vehicles) or the like, use referring expressions to identify particular intended referents (e.g. components and sub components). In some examples, a referring expression is any noun phrase, or surrogate for a noun phrase, whose function in a text is to identify an individual person, place, object, or a set of persons, places, objects or the like. Referring expressions are generated based on the discourse context (e.g. the previously generated text) and the genre of the text (e.g. engineering maintenance manuals often use different referring expressions from operational manuals).
However, in order to generate referring expressions that describe an entity, a decision must be made about how much information to include in each referring expression. For example, a referring expression that has limited information may cause a reader to become confused, whereas an expression with too much information may reduce readability and effectiveness of a text. By way of further example, in a complex system, one or more of the following referring expressions that describe a blade component may be generated based on a hierarchy (see e.g.
In order to generate or otherwise select a referring expression to be included in a textual output, methods, apparatuses, and computer program products are described herein that are configured to generate a referring expression in the form of a referring noun phrase using a part-of hierarchy, a reference model and/or a discourse model. In particular, a microplanner, having a referring expression generation system, may be configured to generate the referring expression based on a default descriptor for a particular entity to be referred to (the intended referent) and one or more salient ancestors of the intended referent. Further, the referring expression generation system may also be configured to determine a previously referred-to entity and, as such, may then identify a lowest common ancestor in the hierarchy of the intended referent and the previously referred-to entity. A salient ancestor (e.g. a prominent or important parent in the hierarchy) may also be determined for the intended referent. In an instance in which the salient ancestor is higher than or equal to the lowest common ancestor, then the default descriptor of the intended referent may become the referring expression. However, in an instance in which the salient ancestor of the intended referent is lower in the hierarchy than the lowest common ancestor, the default descriptors of one or more salient ancestors (e.g. via one or more salient links) of an intended referent may be formed together with a default descriptor of the intended referent to generate a referring expression.
A message store 110 or knowledge pool is configured to store one or more messages that are accessible by the natural language generation system 102. Messages are language independent data structures that correspond to informational elements in a text and/or collect together underlying data, referred to as slots, arguments or features, which can be presented within a fragment of natural language such as a phrase or sentence. Messages may be represented in various ways; for example, each slot may consist of a named attribute and its corresponding value; these values may recursively consist of sets of named attributes and their values, and each message may belong to one of a set of predefined types. The concepts and relationships that make up messages may be drawn from an ontology (e.g. a domain model 112) that formally represents knowledge about the application scenario. In some examples, the domain model 112 is a representation of information about a particular domain. For example, a domain model may contain an ontology that specifies the kinds of objects, instances, concepts and/or the like that may exist in the domain in concrete or abstract form, properties that may be predicated of the objects, concepts and the like, relationships that may hold between the objects, concepts and the like, and representations of any specific knowledge that is required to function in the particular domain.
In some examples, messages are created based on a requirements analysis as to what is to be communicated for a particular scenario (e.g. for a particular domain or genre). A message typically corresponds to a fact about the underlying data (for example, the existence of some observed event) that could be expressed via a simple sentence (although it may ultimately be realized by some other linguistic means). For example, to linguistically describe an object, such as an engine, a user may want to know which engine is being referred to, a status of the engine, a condition of the engine and/or the like. In some cases, the user may not want to know an engine temperature, but instead want to be warned in an instance in which the engine temperature is at a dangerous level. For example, “the right engine is too hot.” In other examples, the engine being too hot may be linked to a resultant condition, for example “after investigating the crash, it appears the right engine was too hot.”
In some examples, a message is created in an instance in which the raw input data warrants the construction of such a message. For example, a wind message would only be constructed in an instance in which wind data was present in the raw input data. Alternatively or additionally, while messages may correspond directly to observations taken from a raw data input, others, however, may be derived from the observations by means of a process of inference or based on one or more detected events. For example, the presence of rain may be indicative of other conditions, such as the potential for snow at some temperatures.
Messages may be instantiated based on many variations of source data, such as but not limited to time series data, time and space data, data from multiple data channels, an ontology, sentence or phrase extraction from one or more texts, a text, survey responses, structured data, unstructured data and/or the like. For example, in some cases, messages may be generated based on text related to multiple news articles focused on the same or similar news story in order to generate a news story. Whereas, in other examples, messages may be built based on survey responses and/or event data.
Messages may be annotated with an indication of their relative importance; this information can be used in subsequent processing steps or by the natural language generation system 102 to make decisions about which information may be conveyed and which information may be suppressed. Alternatively or additionally, messages may include information on relationships between the one or more messages.
In some example embodiments, a natural language generation system, such as natural language generation system 102, is configured to generate phrases, sentences, text or the like which may take the form of a natural language text. The natural language generation system 102 comprises a document planner 130, a microplanner 132 and/or a realizer 134. The natural language generation system 102 may also be in data communication with the message store 110, the domain model 112 and/or the linguistic resources 114. In some examples, the linguistic resources include, but are not limited to, text schemas, aggregation rules, reference rules, lexicalization rules and/or grammar rules that may be used by one or more of the document planner 130, the microplanner 132 and/or the realizer 134. Other natural language generation systems may be used in some example embodiments, such as a natural language generation system as described in Building Natural Language Generation Systems by Ehud Reiter and Robert Dale, Cambridge University Press (2000), which is incorporated by reference in its entirety herein.
The document planner 130 is configured to input the one or more messages from the message store 110. The document planner 130 is further configured to determine how to arrange those messages in order to describe the patterns in the one or more data channels derived from the raw input data. The document planner 130 may comprise a content determination process that is configured to select the messages, such as the messages that contain a representation of the data that is to be output via a natural language text.
The document planner 130 may also comprise a structuring process that determines the order of messages to be included in a text. In some example embodiments, the document planner 130 may access one or more text schemas for the purposes of content determination and document structuring. A text schema is a rule set that defines the order in which a number of messages are to be presented in a document. For example, a medication injection message may be described prior to a heart rate spike message. In other examples, a steady respiration rate message may be described after, but in relation to, the heart rate spike message.
The output of the document planner 130 may be a tree-structured object or other data structure that is referred to as a document plan. In an instance in which a tree-structured object is chosen for the document plan, the leaf nodes of the tree may contain the messages, and the intermediate nodes of the tree structure object may be configured to indicate how the subordinate nodes are related (e.g. elaboration, consequence, contrast, sequence and/or the like) to each other.
The microplanner 132 is configured to construct a text specification based on the document plan from the document planner 130, such that the document plan may be expressed in natural language. In some example embodiments, the microplanner 132 may perform aggregation, lexicalization and referring expression generation. In some examples, aggregation includes, but is not limited to, determining whether two or more messages can be combined together linguistically to produce a more complex phrase specification. For example, one or more messages may be aggregated so that both of the messages can be described by a single sentence. In some examples, lexicalization includes, but is not limited to, choosing particular words for the expression of concepts and relations. In some examples, referring expression generation includes, but is not limited to, choosing how to refer to an entity so that it can be unambiguously identified by the reader. Referring expression generation is further described with respect to at least
A realizer 134 is configured to traverse a text specification output by the microplanner 132 to express the text specification in natural language. The realization process that is applied to each phrase specification makes use of a grammar (e.g. the grammar of the linguistic resources 114) which specifies the valid syntactic structures in the language and further provides a way of mapping from phrase specifications into the corresponding natural language sentences. The output of the process is, in some example embodiments, a natural language text. In some examples, the natural language text may include embedded mark-up.
In some example embodiments and in order to generate the referring expression, the referring expression generation system 208 is configured to access or otherwise be in data communication with a data model 112 that may additionally comprise or otherwise embodies at least a hierarchy 202 (e.g. a part-of hierarchy such as the hierarchy shown in
In some examples, a salient ancestor is an ancestor of an intended referent in the hierarchy 202 that may be added to a referring expression in an instance in which it is insufficient to use the default descriptor of the intended referent alone. In some examples, the salient ancestor is the intended referent's parent in the hierarchy 202; however, in other examples one or more levels within the hierarchy 202 may be skipped or marked as to be ignored. For example and with reference to
In an instance in which the salient ancestor is null or the intended referent is otherwise indicated as always salient, then the intended referent may be described without reference to a salient ancestor. For example, in a geographic ontology or hierarchy, Chicago and Springfield would both be beneath the state of Illinois; however Chicago would likely be marked as always salient (because in most contexts “Chicago” by itself is sufficient). On the other hand, Springfield would not be marked as always salient and would have Illinois as a salient ancestor, because “Springfield” without “Illinois” would not be meaningful. Further, in a sports ontology, a player such as David Beckham or Ronaldo may be marked as always salient, whereas Freddi Montero may require a salient ancestor of Seattle Sounders FC in a textual output. In some examples, Seattle Sounders may need a further salient ancestor of Major League Soccer, in other example textual outputs.
In some example embodiments a discourse model 206 is embodied by or may be accessed by the microplanner 132. The discourse model 206 is configured to record the entities previously referred to in the present text (e.g. entities mentioned in previous phrase specifications), along with the referring expressions that were used to refer to them. For example, and with reference to
In some example embodiments, the referring expression generation system 208 may determine the lowest common ancestor in the hierarchy 202 between an intended referent and the previous referent. Using the lowest common ancestor, the intended referent and the salient ancestors, a referring expression, for example in the form of a referring noun phrase, is generated by the referring expression generation system 208 by including the default descriptors of the intended referent and its ancestors (e.g. by following the salient ancestor links) until the lowest common ancestor, or one of its ancestors that is salient, is reached. The generation of the referring expression is further described with reference to
In block 304, the referring expression generation system 208 may access the discourse model 206 to obtain the previous entity referred to. The previous entity referred to is the last or prior entity that was the intended referent in the generation of a referring expression. The previous entity referred to may then be identified or otherwise located in the hierarchy by the referring expression generation system 208. Using the previous entity referred to, the referring expression generation system 208 may be configured to set a lowest common ancestor to be the lowest entity within the hierarchy that is an ancestor of both the intended referent and the previous entity referred to in block 306. In an instance in which the previous entity referred to is null, then the lowest common ancestor may be set to a root entity of the hierarchy (e.g. Super Puma in
In block 308, the default descriptor of the intended referent in the reference model is added to a descriptor queue. In some example embodiments, the descriptor queue is initialized as an empty queue prior to the first instance of block 308. Alternatively or additionally, the process shown in
As shown in block 312, a salient ancestor of the intended referent in the reference model may be identified, such as via the reference model 204. At decision block 314, the referring expression generation system 208 is configured to determine whether the salient ancestor is lower in the hierarchy than the lowest common ancestor. If so, then at block 316, the current salient ancestor is set as a new target referent. In block 318, the default descriptor for the new target referent is added to the descriptor queue and a new salient ancestor for the new target referent is determined in block 312 The process of blocks 312-318 continues until, at decision block 314, the salient ancestor of the current target referent is higher than or equal to the lowest common ancestor. As noted, during each iteration through blocks 312-318, the default descriptor for the target referent is added to the descriptor queue. As such, the hierarchy is traversed using salient ancestor links. For example salient ancestor links may be represented as:
(1) start with TARGET
(2) go to Salient Ancestor (TARGET)
(3) go to Salient Ancestor (Salient Ancestor (TARGET))
(4) go to Salient Ancestor (Salient Ancestor (Salient Ancestor (TARGET))
Alternatively or additionally, in some examples other methods of traversal may be used such as, but not limited to, traversing each hierarchy and skipping those entities marked as to be ignored, traversing the hierarchy and including parent entities, and/or the like.
At block 320, the first element of the descriptor queue is removed and designated as the head noun of a referring noun phrase. In some example embodiments, the head noun may be assigned a determiner of “the”. For example if the intended referent was “Super Puma”, the default descriptor may be stored in the referring noun phrase as “the Super Puma”.
At decision block 322, in an instance in which the descriptor queue is not empty, it is determined whether a predetermined premodifier count as been reached. In some examples, a premodifier count is predetermined and indicates the maximum number of premodifiers that may be placed before the head noun in the referring noun phrase. In an instance in which the premodifier count has not been reach or satisfied, then, at block 324, the default descriptor of the first element of the descriptor queue is set as a premodifier to the head noun in the referring noun phrase. For example, in an instance in which a blade is the intended referent, “turbine” may be added as a premodifier resulting in a referring expression “the turbine blades”. The premodifier count is also incremented in block 324. Such a process continues until the premodifier count is reached or the descriptor queue is empty.
In an instance in which the maximum premodifier count is reached or the descriptor queue is empty, then at decision block 326, it is determined whether the descriptor queue is empty. If the descriptor queue is not empty, then at block 328, the first element of the descriptor queue is set as a postmodifier to the head noun in the referring noun phrase. In some examples the first element is added to a prepositional phrase having the proposition “of” and is then added to the referring noun phrase. For example, in an instance in which a blade is the intended referent and “turbine” is the premodifier, “right engine” may be added as the postmodifier resulting in a referring expression “the turbine blade of the right engine”. Such a process continues until the descriptor queue is empty.
At block 330, the referring noun phrase is returned as the referring expression for use in a phrase specification and eventually the textual output of the natural language generation system 102. Alternatively or additionally, the discourse model 206 is updated to reflect the most recently identified intended referent.
Alternatively or additionally, one or more entities may not have a default descriptor in a reference model. For example, in the hierarchy of
By way of example, in order to generate a referring expression for an entity that does not have a default descriptor, the referring expression generation system 208 may, in some example embodiments, determine whether the intended referent has been previously referred to. In an instance in which the intended referent has not been previously referred to, then the referring noun phrase may include “a” and the class or type of the intended referent (e.g. a gear). In an instance in which the intended referent has been previously referred to, then the referring expression generation system 208 may determine the previous references in the one or more phrase specifications to a same class or type via the discourse model. In an instance in which the intended referent is the most recently referred-to entity in the previously referred-to entities then the referring noun phrase may include the determiner “the” and the intended referent class or type name. Otherwise the referring noun phrase is generated to include “one of the” and the entity is set to plural (e.g. “one of the gears”). Alternatively or additionally, sets may be referred to in a same or similar manner. For example, if referring to multiple unnamed entities of the same type and in the same hierarchy position (e.g. the gears), phrases such as “four of the gears” or “all of the gears” may be returned.
Text was taken from Section 1.12.2 of an official air accident report (http://www.aaib.gov.uk/cms_resources/2-2011%20G-REDL.pdf).
For example in order to describe the blades 402, the referring expression generation system 210 is configured to determine a previous entity referred to in the text, such as via the discourse model 206. In this example, the previous entity referred to in the text was the free turbine case 404. Therefore, in this example, the lowest common ancestor in the hierarchy, between the free turbine case 404 and the blades 402, is the right engine 406. A reference model, such as reference model 204, may indicate that the turbine 408 is the salient ancestor of the blades 402. As such, the blades 402 are designated to be referred to by the head noun of a referring noun phrase. Because the turbine 408 is located beneath the lowest common ancestor in the hierarchy, the turbine 408 is then set as the target referent and its salient ancestor, the right engine 406, is determined. In this example, the right engine 406 is the salient ancestor of the turbine 408 and is also the lowest common ancestor and therefore the process ends. The referring noun phrase may be then generated by the referring expression generation system 210 having “blades” as the head noun and having “turbine” as a premodifier or postmodifier. For example, the referring noun phrase may be: “the turbine blades” or “the blades of the turbine”.
In the example embodiment shown, computing system 500 comprises a computer memory (“memory”) 501, a display 502, one or more processors 503, input/output devices 504 (e.g., keyboard, mouse, CRT or LCD display, touch screen, gesture sensing device and/or the like), other computer-readable media 505, and communications interface 506. The processor 503 may, for example, be embodied as various means including one or more microprocessors with accompanying digital signal processor(s), one or more processor(s) without an accompanying digital signal processor, one or more coprocessors, one or more multi-core processors, one or more controllers, processing circuitry, one or more computers, various other processing elements including integrated circuits such as, for example, an application-specific integrated circuit (ASIC) or field-programmable gate array (FPGA), or some combination thereof. Accordingly, although illustrated in
The natural language generation system 102 is shown residing in memory 501. The memory 501 may comprise, for example, transitory and/or non-transitory memory, such as volatile memory, non-volatile memory, or some combination thereof. Although illustrated in
In other embodiments, some portion of the contents, some or all of the components of the natural language generation system 102 may be stored on and/or transmitted over the other computer-readable media 505. The components of the natural language generation system 102 preferably execute on one or more processors 503 and are configured to enable operation of a configurable microplanner, as described herein.
Alternatively or additionally, other code or programs 530 (e.g., an administrative interface, a Web server, and the like) and potentially other data repositories, such as other data sources 540, also reside in the memory 501, and preferably execute on one or more processors 503. Of note, one or more of the components in
The natural language generation system 102 is further configured to provide functions such as those described with reference to
In an example embodiment, components/modules of the natural language generation system 102 are implemented using standard programming techniques. For example, the natural language generation system 102 may be implemented as a “native” executable running on the processor 503, along with one or more static or dynamic libraries. In other embodiments, the natural language generation system 102 may be implemented as instructions processed by a virtual machine that executes as one of the other programs 530. In general, a range of programming languages known in the art may be employed for implementing such example embodiments, including representative implementations of various programming language paradigms, including but not limited to, object-oriented (e.g., Java, C++, C#, Visual Basic.NET, Smalltalk, and the like), functional (e.g., ML, Lisp, Scheme, and the like), procedural (e.g., C, Pascal, Ada, Modula, and the like), scripting (e.g., Perl, Ruby, Python, JavaScript, VBScript, and the like), and declarative (e.g., SQL, Prolog, and the like).
The embodiments described above may also use synchronous or asynchronous client-server computing techniques. Also, the various components may be implemented using more monolithic programming techniques, for example, as an executable running on a single processor computer system, or alternatively decomposed using a variety of structuring techniques, including but not limited to, multiprogramming, multithreading, client-server, or peer-to-peer, running on one or more computer systems each having one or more processors. Some embodiments may execute concurrently and asynchronously, and communicate using message passing techniques. Equivalent synchronous embodiments are also supported. Also, other functions could be implemented and/or performed by each component/module, and in different orders, and by different components/modules, yet still achieve the described functions.
In addition, programming interfaces to the data stored as part of the natural language generation system 102, such as by using one or more application programming interfaces can be made available by mechanisms such as through application programming interfaces (API) (e.g. C, C++, C#, and Java); libraries for accessing files, databases, or other data repositories; through scripting languages such as XML; or through Web servers, FTP servers, or other types of servers providing access to stored data. The message store 110, the domain model 112 and/or the linguistic resources 114 may be implemented as one or more database systems, file systems, or any other technique for storing such information, or any combination of the above, including implementations using distributed computing techniques. Alternatively or additionally, the message store 110, the domain model 112 and/or the linguistic resources 114 may be local data stores but may also be configured to access data from the remote data sources 556.
Different configurations and locations of programs and data are contemplated for use with techniques described herein. A variety of distributed computing techniques are appropriate for implementing the components of the illustrated embodiments in a distributed manner including but not limited to TCP/IP sockets, RPC, RMI, HTTP, Web Services (XML-RPC, JAX-RPC, SOAP, and the like). Other variations are possible. Also, other functionality could be provided by each component/module, or existing functionality could be distributed amongst the components/modules in different ways, yet still achieve the functions described herein.
Furthermore, in some embodiments, some or all of the components of the natural language generation system 102 may be implemented or provided in other manners, such as at least partially in firmware and/or hardware, including, but not limited to one or more ASICs, standard integrated circuits, controllers executing appropriate instructions, and including microcontrollers and/or embedded controllers, FPGAs, complex programmable logic devices (“CPLDs”), and the like. Some or all of the system components and/or data structures may also be stored as contents (e.g., as executable or other machine-readable software instructions or structured data) on a computer-readable medium so as to enable or configure the computer-readable medium and/or one or more associated computing systems or devices to execute or otherwise use or provide the contents to perform at least some of the described techniques. Some or all of the system components and data structures may also be stored as data signals (e.g., by being encoded as part of a carrier wave or included as part of an analog or digital propagated signal) on a variety of computer-readable transmission mediums, which are then transmitted, including across wireless-based and wired/cable-based mediums, and may take a variety of forms (e.g., as part of a single or multiplexed analog signal, or as multiple discrete digital packets or frames). Such computer program products may also take other forms in other embodiments. Accordingly, embodiments of this disclosure may be practiced with other computer system configurations.
As is shown in operation 604, an apparatus may include means, such as the microplanner 132, the hierarchy 202, the discourse model 206, the reference system 208, the processor 503, or the like, for determining a lowest common ancestor for the intended referent and a previously referred-to entity within a part-of hierarchy, such as an equipment part-of hierarchy. As is shown in operation 606, an apparatus may include means, such as the microplanner 132, the hierarchy 202, the discourse model 206, the referring expression generation system 208, the processor 503, or the like, for determining the previously referred-to entity based on a last entity mentioned in a discourse model. In some example embodiments, the previously referred-to entity is set to a root component of the part-of hierarchy in an instance in which the previous reference is set to null.
As is shown in operation 608, an apparatus may include means, such as the microplanner 132, the hierarchy 202, the referring expression generation system 208, the processor 503, or the like, for determining that a salient ancestor of the intended referent is higher than or equal to the lowest common ancestor in the part-of hierarchy, such that the referring noun phrase comprises the default descriptor of the intended referent. As is shown in operation 610, an apparatus may include means, such as the microplanner 132, the hierarchy 202, the referring expression generation system 208, the processor 503, or the like, for determining that a salient ancestor of the intended referent is lower in the part-of hierarchy than a lowest common ancestor in an instance in which the intended referent is marked as not salient.
As is shown in operation 612, an apparatus may include means, such as the microplanner 132, the hierarchy 202, the reference model 204, the referring expression generation system 208, the processor 503, or the like, for causing the salient ancestor to be set as a current target referent and a new salient ancestor to be determined for the current target referent, wherein the default descriptor of each current target referent is added to the referring noun phrase and the part-of hierarchy is traversed via salient ancestor links until the new salient ancestor of the current target referent is higher than or equal to the lowest common ancestor.
In some example embodiments, the referring noun phrase comprises a predetermined maximum number of premodifiers of the default descriptor of the intended referent, wherein the premodifiers comprise one or more default descriptors of the one or more parts of the part-of hierarchy traversed. In additional example embodiments, the referring noun phrase comprises a number of postmodifiers of the default descriptor of the intended referent, wherein the postmodifiers comprise the remaining one or more default descriptors of the one or more parts of the part-of hierarchy traversed not included as premodifiers.
Accordingly, blocks of the flowchart support combinations of means for performing the specified functions and combinations of operations for performing the specified functions. It will also be understood that one or more blocks of the flowcharts′, and combinations of blocks in the flowchart, can be implemented by special purpose hardware-based computer systems which perform the specified functions, or combinations of special purpose hardware and computer instructions.
In some example embodiments, certain ones of the operations herein may be modified or further amplified as described below. Moreover, in some embodiments additional optional operations may also be included (some examples of which are shown in dashed lines in
Many modifications and other embodiments of the inventions set forth herein will come to mind to one skilled in the art to which these inventions pertain having the benefit of the teachings presented in the foregoing descriptions and the associated drawings. Therefore, it is to be understood that the inventions are not to be limited to the specific embodiments disclosed and that modifications and other embodiments are intended to be included within the scope of the appended claims. Moreover, although the foregoing descriptions and the associated drawings describe example embodiments in the context of certain example combinations of elements and/or functions, it should be appreciated that different combinations of elements and/or functions may be provided by alternative embodiments without departing from the scope of the appended claims. In this regard, for example, different combinations of elements and/or functions than those explicitly described above are also contemplated as may be set forth in some of the appended claims. Although specific terms are employed herein, they are used in a generic and descriptive sense only and not for purposes of limitation.
This application is a continuation of U.S. application Ser. No. 14/634,119, filed Feb. 27, 2015, which is a continuation of International Application No. PCT/US2012/053183, filed Aug. 30, 2012, all of which are hereby incorporated herein by reference.
| Number | Date | Country | |
|---|---|---|---|
| Parent | 14634119 | Feb 2015 | US |
| Child | 15093337 | US | |
| Parent | PCT/US2012/053183 | Aug 2012 | US |
| Child | 14634119 | US |
