利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

9 条记录 (耗时 0.019 秒)

    Context saliency-based deictic parser for natural language generation
    3.
    发明授权
    Context saliency-based deictic parser for natural language generation 有权

    公开(公告)号：US11042708B1

    公开(公告)日：2021-06-22

    申请号：US16233746

    申请日：2018-12-27

    申请人： Narrative Science Inc.

    发明人： Michael Tien Thinh Pham ,  Nathan William Krapf ,  Stephen Emmanuel Hudson ,  Clayton Nicholas Norris

    IPC分类号： G06F40/30 ,  G06F40/205 ,  G06F40/295

    摘要： NLG techniques are disclosed that apply computer technology to sentence data for performing entity referencing. For example, a processor can parse sentence data in a defined window of sentence data into a list of entity terms and a plurality of classifications associated with the listed entity terms. A processor can also compute a plurality of context saliency scores for a plurality of the listed entity terms based on the classifications associated with the listed entity terms. For new sentence data that refers to an entity term from the entity term list, a processor can select a referring term for referencing that entity term from a list of candidate referring terms based on the context saliency scores for the entity terms. A processor can then form the new sentence data such that the new sentence data includes the selected referring term to refer to the at least one entity term.

    Applied artificial intelligence technology for conversational inferencing
    4.
    发明授权
    Applied artificial intelligence technology for conversational inferencing 有权

    公开(公告)号：US10755046B1

    公开(公告)日：2020-08-25

    申请号：US16277000

    申请日：2019-02-15

    申请人： Narrative Science Inc.

    发明人： Maia Lewis Meza ,  Clayton Nicholas Norris ,  Michael Justin Smathers ,  Daniel Joseph Platt ,  Nathan D. Nichols

    IPC分类号： G06F17/27 ,  G06F17/21 ,  G06F40/279 ,  G06F40/30 ,  G06F40/211 ,  G06F40/253

    摘要： Disclosed herein is an NLP system that is able to extract meaning from a natural language message using improved parsing techniques. Such an NLP system can be used in concert with an NLG system to interactively interpret messages and generate response messages in an interactive conversational stream. The parsing can include (1) named entity recognition that contextualizes the meanings of words in a message with reference to a knowledge base of named entities understood by the NLP and NLG systems, (2) syntactically parsing the message to determine a grammatical hierarchy for the named entities within the message, (3) reduction of recognized named entities into aggregations of named entities using the determined grammatical hierarchy and reduction rules to further clarify the message's meaning, and (4) mapping the reduced aggregation of named entities to an intent or meaning, wherein this intent/meaning can be used as control instructions for an NLG process.

    Applied artificial intelligence technology for conversational inferencing using named entity reduction
    5.
    发明授权
    Applied artificial intelligence technology for conversational inferencing using named entity reduction 有权

    公开(公告)号：US11030408B1

    公开(公告)日：2021-06-08

    申请号：US16277006

    申请日：2019-02-15

    申请人： Narrative Science Inc.

    发明人： Maia Lewis Meza ,  Clayton Nicholas Norris ,  Michael Justin Smathers ,  Daniel Joseph Platt ,  Nathan D. Nichols

    IPC分类号： G06F40/295 ,  G06F40/211 ,  G06F40/268 ,  G06F40/30

    摘要： Disclosed herein is an NLP system that is able to extract meaning from a natural language message using improved parsing techniques. Such an NLP system can be used in concert with an NLG system to interactively interpret messages and generate response messages in an interactive conversational stream. The parsing can include (1) named entity recognition that contextualizes the meanings of words in a message with reference to a knowledge base of named entities understood by the NLP and NLG systems, (2) syntactically parsing the message to determine a grammatical hierarchy for the named entities within the message, (3) reduction of recognized named entities into aggregations of named entities using the determined grammatical hierarchy and reduction rules to further clarify the message's meaning, and (4) mapping the reduced aggregation of named entities to an intent or meaning, wherein this intent/meaning can be used as control instructions for an NLG process.

    Context saliency-based deictic parser for natural language processing
    6.
    发明授权
    Context saliency-based deictic parser for natural language processing 有权

    公开(公告)号：US11816438B2

    公开(公告)日：2023-11-14

    申请号：US17326042

    申请日：2021-05-20

    申请人： Narrative Science Inc.

    发明人： Michael Tien Thinh Pham ,  Nathan William Krapf ,  Stephen Emmanuel Hudson ,  Clayton Nicholas Norris

    IPC分类号： G06F40/30 ,  G06F40/205 ,  G06F40/295

    CPC分类号： G06F40/30 ,  G06F40/205 ,  G06F40/295

    摘要： NLP techniques are disclosed that apply computer technology to sentence data for performing entity referencing. For example, a processor can parse sentence data in a defined window of sentence data into a list of entity terms and a plurality of classifications associated with the listed entity terms. A processor can also a plurality of context saliency scores for a plurality of the listed entity terms based on the classifications associated with the listed entity terms as well as maintain a list of referring terms corresponding to the listed entity terms. For new sentence data that includes a referring term from the referring term list, a processor can (i) select a corresponding entity term on the entity term list based on the context saliency scores for the entity terms, and (ii) infer that the referring term in the new sentence data refers to the selected corresponding entity term.

    Applied artificial intelligence technology for building a knowledge base using natural language processing
    7.
    发明授权
    Applied artificial intelligence technology for building a knowledge base using natural language processing 有权

    公开(公告)号：US11182556B1

    公开(公告)日：2021-11-23

    申请号：US16277008

    申请日：2019-02-15

    申请人： Narrative Science Inc.

    发明人： Maia Lewis Meza ,  Clayton Nicholas Norris ,  Michael Justin Smathers ,  Daniel Joseph Platt ,  Nathan D. Nichols

    IPC分类号： G06F40/295 ,  G06F40/30 ,  G06F40/56 ,  G06F40/211

    摘要： Disclosed herein is an NLP system that is able to extract meaning from a natural language message using improved parsing techniques. Such an NLP system can be used in concert with an NLG system to interactively interpret messages and generate response messages in an interactive conversational stream. The parsing can include (1) named entity recognition that contextualizes the meanings of words in a message with reference to a knowledge base of named entities understood by the NLP and NLG systems, (2) syntactically parsing the message to determine a grammatical hierarchy for the named entities within the message, (3) reduction of recognized named entities into aggregations of named entities using the determined grammatical hierarchy and reduction rules to further clarify the message's meaning, and (4) mapping the reduced aggregation of named entities to an intent or meaning, wherein this intent/meaning can be used as control instructions for an NLG process.

    Context Saliency-Based Deictic Parser for Natural Language Processing
    8.
    发明申请
    Context Saliency-Based Deictic Parser for Natural Language Processing 有权

    公开(公告)号：US20210271824A1

    公开(公告)日：2021-09-02

    申请号：US17326042

    申请日：2021-05-20

    申请人： Narrative Science Inc.

    发明人： Michael Tien Thinh Pham ,  Nathan William Krapf ,  Stephen Emmanuel Hudson ,  Clayton Nicholas Norris

    IPC分类号： G06F40/30 ,  G06F40/295 ,  G06F40/205

    摘要： NLP techniques are disclosed that apply computer technology to sentence data for performing entity referencing. For example, a processor can parse sentence data in a defined window of sentence data into a list of entity terms and a plurality of classifications associated with the listed entity terms. A processor can also a plurality of context saliency scores for a plurality of the listed entity terms based on the classifications associated with the listed entity terms as well as maintain a list of referring terms corresponding to the listed entity terms. For new sentence data that includes a referring term from the referring term list, a processor can (i) select a corresponding entity term on the entity term list based on the context saliency scores for the entity terms, and (ii) infer that the referring term in the new sentence data refers to the selected corresponding entity term.

    Context saliency-based deictic parser for natural language processing
    9.
    发明授权
    Context saliency-based deictic parser for natural language processing 有权

    公开(公告)号：US11042709B1

    公开(公告)日：2021-06-22

    申请号：US16233776

    申请日：2018-12-27

    申请人： Narrative Science Inc.

    发明人： Michael Tien Thinh Pham ,  Nathan William Krapf ,  Stephen Emmanuel Hudson ,  Clayton Nicholas Norris

    IPC分类号： G06F40/30 ,  G06F40/205 ,  G06F40/295

    摘要： Context Saliency-Based Deictic Parser for Natural Language Processing NLP techniques are disclosed that apply computer technology to sentence data for performing entity referencing. For example, a processor can parse sentence data in a defined window of sentence data into a list of entity terms and a plurality of classifications associated with the listed entity terms. A processor can also a plurality of context saliency scores for a plurality of the listed entity terms based on the classifications associated with the listed entity terms as well as maintain a list of referring terms corresponding to the listed entity terms. For new sentence data that includes a referring term from the referring term list, a processor can (i) select a corresponding entity term on the entity term list based on the context saliency scores for the entity terms, and (ii) infer that the referring term in the new sentence data refers to the selected corresponding entity term.