公开(公告)号：US07203668B2

公开(公告)日：2007-04-10

申请号：US10322504

申请日：2002-12-19

申请人： John O. Lamping ,  Richard S. Crouch ,  Mary Dalrymple ,  Hadar Shemtov

发明人： John O. Lamping ,  Richard S. Crouch ,  Mary Dalrymple ,  Hadar Shemtov

IPC分类号： G06F17/00 ,  G06N5/02

CPC分类号： G06F17/271 ,  G06F17/274 ,  G06F17/2785

摘要： Techniques managing syntactic and semantic ambiguity allow two different kinds of processing and representation of ambiguity to work together. The techniques allow linear logic semantic assembly to work with packed functional (f) structures and provide for contexted version of linear logic where semantic contributions are read from the packed functional (f) structure and pre-pended with the contents of the functional (f) structure to which they pertain. Linear logic reasoning may then be performed in the contexted linear logic to derive possible meanings from the contexted contributions from the packed functional (f) structure. Deductions in the contexted linear logic do not require fully expanding each syntactic parse. Techniques applying skeleton/modifier techniques to contexted reasoning are provided by creating a contexted modifier applicable only for certain syntactic readings. These techniques recognize both quantifier scope ambiguity and attachment ambiguity in a representation that uses efficient skeleton/modifier representation where possible and contexted representation otherwise.

摘要翻译： 管理句法和语义歧义的技术允许两种不同的处理方式和歧义的表示方式一起工作。 这些技术允许线性逻辑语义组合与包装功能（f）结构一起工作，并提供线性逻辑的有争议的版本，其中从包装功能（f）结构读取语义贡献，并且预先与功能（f） 他们所属的结构。 然后线性逻辑推理可以在有争议的线性逻辑中执行，以从包装功能（f）结构的有争议的贡献中导出可能的含义。 扣除线性逻辑不需要完全扩展每个句法解析。 通过创建一个仅适用于某些句法读数的contexted修饰来提供应用骨架/修饰技术来解决推理的技术。 这些技术在可能的情况下使用有效的骨架/修饰符表示的表示中识别量词范围模糊度和附加歧义，否则表示。

公开(公告)号：US07313515B2

公开(公告)日：2007-12-25

申请号：US11415609

申请日：2006-05-01

申请人： Richard S. Crouch ,  Tracy Holloway King

发明人： Richard S. Crouch ,  Tracy Holloway King

IPC分类号： G06F17/27

CPC分类号： G06N5/02

摘要： Techniques are provided for detecting entailment and contradiction. Packed knowledge representations for a premise and conclusion text are determined comprising facts about the relationships between concept and/or context denoting terms. Concept and context alignments are performed based on alignments scores. A union is determined. Terms are marked as to their origin and conclusion text terms replaced with by corresponding terms from the premise text. Subsumption and specificity, instantiability, spatio-temporal and relationship based packed rewrite rules are applied in conjunction with the context denoting facts to remove entailed terms and to mark contradictory facts within the union. Entailment is indicated by a lack of any facts from the packed knowledge representation of the conclusion in the union. Entailment and contradiction markers are then displayed.

公开(公告)号：US07610190B2

公开(公告)日：2009-10-27

申请号：US10684508

申请日：2003-10-15

申请人： Livia Polanyi ,  Martin H. Van Den Berg ,  Giovanni Lorenzo Thione ,  Richard S. Crouch ,  Christopher D. Culy ,  David D. Ahn

发明人： Livia Polanyi ,  Martin H. Van Den Berg ,  Giovanni Lorenzo Thione ,  Richard S. Crouch ,  Christopher D. Culy ,  David D. Ahn

IPC分类号： G06F17/27

CPC分类号： G06F17/279 ,  G06F17/30719 ,  Y10S707/99931 ,  Y10S707/99933 ,  Y10S707/99936

摘要： Techniques are provided for segmenting text into categorized discourse constituents and attaching discourse constituents into a structural representation of discourse. Techniques for determining hybrid structural and non-structural summaries of a text are also provided. A text is segmented based on a theory of discourse analysis into at least a main discourse constituent containing spatio-temporal information about a single event in a possible world view. The discourse constituents are then inserted into a structural representation of discourse. Non-structural techniques are used to determine relevance scores and important discourse constituents are determined. Relevance scores are percolated through the structural representation of discourse to determine supporting preceding discourse constituents that preserve grammaticality. A hybrid text summary is then determined based on the structural representation of the discourse and relevance scores.

摘要翻译： 提供了将文本分割成分类话语组成部分并将话语组成部分附加到话语的结构表示中的技术。 还提供了用于确定文本的混合结构和非结构摘要的技术。 基于话语分析理论将文本分割成至少包含可能的世界观中关于单个事件的时空信息的主要话语成分。 话语成分然后插入话语的结构表示。 非结构性技术用于确定相关性分数，确定重要的话语成分。 相关性分数通过话语的结构表示来抵消，以确定支持保留语法的前面的话语组成部分。 然后基于话语和相关性分数的结构表示来确定混合文本摘要。

公开(公告)号：US08229730B2

公开(公告)日：2012-07-24

申请号：US12201721

申请日：2008-08-29

申请人： Martin H. Van Den Berg ,  Giovanni L. Thione ,  Chad P. Walters ,  Richard S. Crouch

发明人： Martin H. Van Den Berg ,  Giovanni L. Thione ,  Chad P. Walters ,  Richard S. Crouch

IPC分类号： G06F17/30

CPC分类号： G06F17/2785 ,  G06F17/30684

摘要： Methods, systems and computer readable media for finding documents in a data store that match a natural language query submitted by a user are provided. The documents and queries are matched by determining that words within the query have the same relationship to each other as the same words in the document. Documents are semantically analyzed and words in the document are indexed along with the role the word plays in a sentence. The initial semantic role may be generalized using a role hierarchy and stored in the index along with the original role. A similar analysis may be used with the search query to find words used in the same role in both the query and the document.

摘要翻译： 提供了用于在数据存储中查找与用户提交的自然语言查询匹配的文档的方法，系统和计算机可读介质。 通过确定查询中的单词与文档中相同的单词之间具有相同的关系来匹配文档和查询。 对文档进行语义分析，文档中的单词与该单词在一个句子中的作用一起编入索引。 初始语义角色可以使用角色层次结构进行推广，并与原始角色一起存储在索引中。 搜索查询可以使用类似的分析来查找在查询和文档中使用相同角色的单词。

公开(公告)号：US08868562B2

公开(公告)日：2014-10-21

申请号：US12201675

申请日：2008-08-29

申请人： Richard S. Crouch ,  Martin Henk Van Den Berg ,  David Ahn ,  Olga Gurevich ,  Barney D. Pell ,  Livia Polanyi ,  Scott A. Prevost ,  Giovanni Lorenzo Thione

发明人： Richard S. Crouch ,  Martin Henk Van Den Berg ,  David Ahn ,  Olga Gurevich ,  Barney D. Pell ,  Livia Polanyi ,  Scott A. Prevost ,  Giovanni Lorenzo Thione

IPC分类号： G06F7/00 ,  G06F17/30

CPC分类号： G06F17/30705 ,  G06F17/30011 ,  G06F17/30616 ,  G06F17/30619 ,  G06F17/30684

摘要： Methods and computer-readable media for associating words or groups of words distilled from content, such as reported speech or an attitude report, of a document to form semantic relationships collectively used to generate a semantic representation of the content are provided. Semantic representations may include elements identified or parsed from a text portion of the content, the elements of which may be associated with other elements that share a semantic relationship, such as an agent, location, or topic relationship. Relationships may also be developed by associating one element that is in relation to, or is about, another element, thereby allowing for rapid and effective comparison of associations found in a semantic representation with associations derived from queries. The semantic relationships may be determined based on semantic information, such as potential meanings and grammatical functions of each element within the text portion of the content.

摘要翻译： 提供了用于将从内容中提取出来的单词或组的组合的方法和计算机可读介质，例如文档的报告语音或态度报告，以形成共同用于生成内容的语义表示的语义关系。 语义表示可以包括从内容的文本部分识别或解析的元素，其元素可以与共享语义关系的其他元素（例如代理，位置或主题关系）相关联。 还可以通过将一个与另一个元素相关或相关的元素相关联来开发关系，从而允许快速有效地将在语义表示中找到的关联与从查询导出的关联进行比较。 可以基于诸如内容的文本部分中的每个元素的潜在含义和语法功能的语义信息来确定语义关系。