Method and apparatus for referring expression generation
원문보기
IPC분류정보
국가/구분
United States(US) Patent
등록
국제특허분류(IPC7판)
G06F-017/21
G06F-017/27
G06F-017/28
출원번호
US-0634119
(2015-02-27)
등록번호
US-9355093
(2016-05-31)
발명자
/ 주소
Reiter, Ehud Baruch
출원인 / 주소
ARRIA DATA2TEXT LIMITED
대리인 / 주소
Alston & Bird LLP
인용정보
피인용 횟수 :
5인용 특허 :
64
초록▼
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 embodim
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 that a salient ancestor of the intended referent is lower in a part-of hierarchy than a lowest common ancestor. 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.
대표청구항▼
1. A natural language generation method for generating a referring noun phrase for an intended referent found in one or more messages within a document plan, the method comprising: arranging, using a processor, one or more messages in a document plan, wherein messages represent a phrase or a simple
1. A natural language generation method for generating a referring noun phrase for an intended referent found in one or more messages within a document plan, the method comprising: arranging, using a processor, one or more messages in a document plan, wherein messages represent a phrase or a simple sentence and are created in an instance in which an input data stream comprises data that satisfies one or more message requirements, and wherein at least a portion of the input data stream comprises non-linguistic data;identifying an intended referent in a message of the one or more messages to be referred to in a textual output;determining a lowest common ancestor for the intended referent and a previously referred-to entity within a part-of hierarchy;determining a salient ancestor of the intended referent within the part-of hierarchy;generating a referring noun phrase for the intended referent to be included in a textual output by traversing the part-of hierarchy from the salient ancestor to the lowest common ancestor such that a default descriptor is added to a queue for at least a portion of entities traversed in the part-of-hierarchy, wherein the reference noun phrase comprises a default descriptor of the intended referent and one or more default descriptors of one or more parts of the part-of hierarchy that are traversed;generating the textual output comprising the referring noun phrase such that it is displayable on a user interface, wherein the textual output linguistically describes at least a portion of the input data stream; anddisplaying the textual output via a display device. 2. A method according to claim 1, wherein the one or more parts of the part-of hierarchy that are traversed based on one or more salient ancestor links. 3. A method according to claim 1, further comprising: determining that the intended referent is marked as salient; andcausing the referring noun phrase to solely comprise the default descriptor of the intended referent. 4. A method according to claim 1, further comprising: determining that the salient ancestor is equal to the lowest common ancestor; andcausing the referring noun phrase to comprise the default descriptor of the intended referent. 5. A method according to claim 1, further comprising: determining the previously referred-to entity based on a last mentioned entity in a discourse model. 6. A method according to claim 5, wherein the previously referred-to entity is set to a root component of the part-of hierarchy in an instance in which the previously referred-to entity is set to null. 7. A method according to claim 1, wherein the default descriptor of an entity is at least one of a default descriptor, a class name or a type name. 8. A method according to claim 1, further comprising: determining that one or more parts of the part-of hierarchy traversed are marked as ignore, wherein a default descriptor of the one or more parts of the part-of hierarchy that are marked as to be ignored are not included in the referring noun phrase. 9. A method according to claim 1, wherein the default descriptor of an entity further comprises at least one of a class name or a type name. 10. A method according to claim 1, wherein the referring noun phrase comprises a predetermined maximum number of premodifiers of the default descriptor of the intended referent, wherein the predetermined number of premodifiers comprise one or more default descriptors of the one or more parts of the part-of hierarchy that are traversed. 11. A method according to claim 10, wherein the referring noun phrase comprises a set of postmodifiers of the default descriptor of the intended referent, wherein the set of postmodifiers comprise one or more default descriptors of one or more parts of the part-of hierarchy that are traversed that were not included as premodifiers. 12. A method according to claim 1, wherein generating the referring noun phrase further comprises: removing a first element in the queue, wherein the first element is designated as a head noun in the referring noun phase. 13. A method according to claim 12, wherein generating the referring noun phrase further comprises: removing a next element in the queue; andsetting the next element as a premodifier to the head noun; andin instance in which a predetermined premodifier count threshold is satisfied, removing an element from the queue and setting it as a post modifier to the head noun. 14. An apparatus comprising: at least one processor; andat least one memory including computer program code, the at least one memory and the computer program code configured to, with the at least one processor, cause the apparatus to at least:arrange one or more messages in a document plan, wherein messages represent a phrase or a simple sentence and are created in an instance in which an input data stream comprises data that satisfies one or more message requirements, wherein at least a portion of the input data stream comprises non-linguistic data;identify an intended referent in a message of the one or more messages to be referred to in a textual output;determine a lowest common ancestor for the intended referent and a previously referred-to entity within a part-of hierarchy;determine a salient ancestor of the intended referent within the part-of hierarchy;generate a referring noun phrase for the intended referent to be included in a textual output by traversing the part-of hierarchy from the salient ancestor to the lowest common ancestor such that a default descriptor is added to a queue for at least a portion of entities traversed in the part-of-hierarchy, wherein the reference noun phrase comprises a default descriptor of the intended referent and one or more default descriptors of one or more parts of the part-of hierarchy that are traversed;generate the textual output comprising the referring noun phrase such that it is displayable on a user interface, wherein the textual output linguistically describes at least a portion of the input data stream; anddisplay the textual output via a display device. 15. An apparatus according to claim 14, wherein the at least one memory including the computer program code is further configured to, with the at least one processor, cause the apparatus to: determine that the intended referent is marked as salient; andcause the referring noun phrase to solely comprise the default descriptor of the intended referent. 16. An apparatus according to claim 14, wherein the at least one memory including the computer program code is further configured to, with the at least one processor, cause the apparatus to: determine that the salient ancestor is equal to the lowest common ancestor; andcause the referring noun phrase to comprise the default descriptor of the intended referent. 17. An apparatus according to claim 14, wherein the at least one memory including the computer program code is further configured to, with the at least one processor, cause the apparatus to: determine the previously referred-to entity based on a last mentioned entity in a discourse model. 18. A non-transitory computer readable memory medium having program code instructions stored thereon, the program code instructions which when executed by an apparatus cause the apparatus at least to: arrange one or more messages in a document plan, wherein messages represent a phrase or a simple sentence and are created in an instance in which an input data stream comprises data that satisfies one or more message requirements, wherein at least a portion of the input data stream comprises non-linguistic data;identify an intended referent in a message of the one or more messages to be referred to in a textual output;determine a lowest common ancestor for the intended referent and a preyiously referred-to entity within a part-of hierarchy;determine a salient ancestor of the intended referent within the part-of hierarchy;generate a referring noun phrase for the intended referent to be included in a textual output by traversing the part-of hierarchy from the salient ancestor to the lowest common ancestor such that a default descriptor is added to a queue for at least a portion of entities traversed in the part-of-hierarchy, wherein the reference noun phrase comprises a default descriptor of the intended referent and one or more default descriptors of one or more parts of the part-of hierarchy that are traversed;generate the textual output comprising the referring noun phrase such that it is displayable on a user interface, wherein the textual output linguistically describes at least a portion of the input data stream; anddisplay the textual output via a display device. 19. A computer program product according to claim 18, further comprising program code instructions configured to: determine that the intended referent is marked as salient; andcause the referring noun phrase to solely comprise the default descriptor of the intended referent. 20. A computer program product according to claim 18, further comprising program code instructions configured to: determine that the salient ancestor is equal to the lowest common ancestor; andcause the referring noun phrase to comprise the default descriptor of the intended referent. 21. A computer program product according to claim 18, further comprising program code instructions configured to: determine the previously referred-to entity based on a last mentioned entity in a discourse model. 22. A computer program product according to claim 21, wherein the previously referred-to entity is set to a root component of the part-of hierarchy in an instance in which the previously referred-to entity is set to null.
연구과제 타임라인
LOADING...
LOADING...
LOADING...
LOADING...
LOADING...
이 특허에 인용된 특허 (64)
Walker, Marilyn A.; Rambow, Owen Christopher; Rogati, Monica, Automated sentence planning in a task classification system.
Ceusters,Werner; O'Donnell,Mick; Montyne,Frank; Coppens,Frederik; Van Mol,Maarten, Conceptual world representation natural language understanding system and method.
Calistri-Yeh, Randall J.; Yuan, Bo; Osborne, George B.; Snyder, David L., Construction of trainable semantic vectors and clustering, classification, and searching using trainable semantic vectors.
Ferrari,Adam J.; Gourley,David J.; Johnson,Keith A.; Knabe,Frederick C.; Mohta,Vinay B.; Tunkelang,Daniel; Walter,John S., Hierarchical data-driven search and navigation system and method for information retrieval.
Bennett, Ian M.; Babu, Bandi Ramesh; Morkhandikar, Kishor; Gururaj, Pallaki, Interactive speech based learning/training system formulating search queries based on natural language parsing of recognized user queries.
Ringger,Eric; Gamon,Michael; Smets,Martine; Corston Oliver,Simon; Moore,Robert C., Linguistically informed statistical models of constituent structure for ordering in sentence realization for a natural language generation system.
Budzinski Robert L., Memory system for storing and retrieving experience and knowledge with natural language utilizing state representation data, word sense numbers, function codes and/or directed graphs.
Budzinski, Robert L., Memory system for storing and retrieving experience and knowledge with natural language utilizing state representation data, word sense numbers, function codes, directed graphs, context memory, and/or purpose relations.
White Brian F. (Yorktown NY) Bretan Ivan P. (Lidingo SEX) Sanamrad Mohammad A. (Lidingo SEX), Method and apparatus for paraphrasing information contained in logical forms.
Cheng,Hua; Cavedon,Lawrence; Dale,Robert; Weng,Fuliang; Meng,Yao; Peters,Stanley, Method and system for adaptive navigation using a driver's route knowledge.
Burmester, Sven; Lamberg, Klaus; Wewetzer, Christian; Thiessen, Christine, Method of creating a requirement description for testing an embedded system.
Morgan Jerry L. (Urbana IL) Frisch Alan M. (Champaign IL) Hinrichs Erhard W. (Tuebingen DEX), Natural language generation system for producing natural language instructions.
Di Fabbrizio, Giuseppe; Feng, Junlan, Relevance recognition for a human machine dialog system contextual question answering based on a normalization of the length of the user input.
Corston Oliver, Simon; Gamon, Michael; Ringger, Eric; Moore, Robert C.; Zhang, Zhu, Sentence realization model for a natural language generation system.
Begeja, Lee; Rahim, Mazin G.; Gorin, Allen Louis; Shahraray, Behzad; Gibbon, David Crawford; Liu, Zhu; Renger, Bernard S.; Haffner, Patrick Guy; Drucker, Harris; Lewis, Steven Hart, System and method for automatic generation of a natural language understanding model.
Cox, Richard Vandervoort; Eslambolchi, Hossein; Nadji, Behzad; Rahim, Mazin G., System and method for providing a natural language interface to a database.
Birnbaum, Lawrence A.; Hammond, Kristian J.; Allen, Nicholas D.; Templon, John R., System and method for using data and angles to automatically generate a narrative story.
Birnbaum, Lawrence A.; Hammond, Kristian J.; Allen, Nicholas D.; Templon, John R., System and method for using data and derived features to automatically generate a narrative story.
Suda Aruna Rohra,JPX ; Jeyachandran Suresh,JPX, System for generating natural language information from information expressed by concept and method therefor.
Delmonico, Robert M.; Klinger, Tamir; Ray, Bonnie Kathryn; Santhanam, Padmanabhan; Williams, Clay Edwin, Systems and methods for automated interpretation of analytic procedures.
Birnbaum, Lawrence; Hammond, Kristian J.; Nichols, Nathan Drew; Paley, Andrew R., Automatic generation of narratives from data using communication goals and narrative analytics.
Birnbaum, Lawrence; Hammond, Kristian J.; Nichols, Nathan Drew; Paley, Andrew R.; Murata, Shingo; Opulencia, Pia, Automatic generation of narratives from data using communication goals and narrative analytics.
Birnbaum, Lawrence; Hammond, Kristian J.; Nichols, Nathan Drew; Paley, Andrew R.; Murata, Shingo; Opulencia, Pia, Automatic generation of narratives from data using communication goals and narrative analytics.
Birnbaum, Lawrence; Hammond, Kristian J.; Nichols, Nathan Drew; Paley, Andrew R.; Murata, Shingo; Opulencia, Pia, Automatic generation of narratives from data using communication goals and narrative analytics.
Hammond, Kristian J.; Birnbaum, Lawrence; Nichols, Nathan Drew; Paley, Andrew R.; Murata, Shingo; Opulencia, Pia, Automatic generation of narratives from data using communication goals and narrative analytics.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.