Building resources and a model for computing paraphrase based on lexical semantics

构建基于词汇语义的释义计算资源和模型

• 批准号: 17300047
• 负责人: INUI Kentaro
• 金额: $ 10.15万
• 依托单位: Nara Institute of Science and Technology
• 依托单位国家: 日本
• 项目类别: Grant-in-Aid for Scientific Research (B)
• 财政年份: 2005
• 资助国家: 日本
• 起止时间: 2005 至 2007
• 项目状态: 已结题
• 来源: https://kaken.nii.ac.jp/grant/KAKENHI-PROJECT-17300047/
• 关键词: natural language processing; recognizing textual entailment; paraphrase; lexical knowledge; lexical semantics; predicate-argument structure; knowledge acquisition; lexical conceptual structure; 自然言語生成; 動詞

Aiming at building a computational model and computational recourses for computing paraphrase at the level of predicate-argument structure, this research project gained the following results:(i) For paraphrase knowledge, a large-scale hierarchical lexicon of predicate-argument structure was built. The lexicon organizes about 4,000 Japanese basic verbs (about 7,000 senses in total) with predicate-argument structure information in a fine-grained semantic hierarchy so that lexical entries in a semantic class can be regarded as near synonyms. For augmenting this knowledge base, additional knowledge about event relations are extracted from glosses found in a human-use dictionary of Japanese. Over 35,000 relations are extracted and classified into 8 relation types, all of which are considered useful for recognizing paraphrase or textual entailment.(ii) For scaling the basic paraphrase knowledge above, automatic acquisition of semantic relations between events from a large corpus was also exp … More lored. We proposed several extensions to a state-of-the-art method originally designed for entity relation extraction, reporting on the present results of our experiments on a Japanese Web corpus. The results show that (a) there are indeed specific cooccurrence patterns useful for event relation acquisition, (b) the use of cooccurrence samples involving verbal nouns has positive impacts on both re-call and precision, and (c) over five thousand relation instances are acquired from a 500M-sentence Web corpus with a precision of about 66% for action-effect relations.(iii) For building a computational model of paraphrase, we explore the regularity underlying these classes of paraphrases, focusing on the paraphrasing of Japanese light-verb constructions (LVCs). We propose a paraphrasing model for LVCs that is based on transforming the Lexical Conceptual Structures (LCSs) of verbal elements. We also propose a refinement of an existing LCS dictionary. Experimental results show that our LCS-based paraphrasing model characterizes some of the semantic features of those verbs required for generating paraphrases, such as the direction of an action and the relationship between arguments and surface cases. Less

旨在建立一个计算模型和计算反应以计算谓词题材结构级别，该研究项目获得了以下结果：（i）为了释义知识，建立了谓词王志结构的大规模层次结构词典。词典在精细的语义层次结构中组织了大约4,000个日本基本动词（总共7,000个感官），并在语义类别中使用谓词题目的结构信息，以便可以将语义类别的词语视为接近同义词。为了增强这一知识库，从日语的人使用词典中发现的光泽中提取了有关事件关系的其他知识。提取了超过35,000个关系并将其分类为8种关系类型，所有这些关系都被认为对识别释义或文本需要很有用。（ii）用于扩展上面的基本释义知识，从大型语料库中自动获取语义关系，也被经验丰富……更富有。我们向最初设计用于实体关系提取的最新方法提出了几次扩展，并报告了我们在日本网络语料库上实验的当前结果。结果表明，（a）确实存在针对事件关系获取有用的特定特定的同时发性模式，（b）使用涉及言语名词的cooccrocccrocccroccercrence样品对重新打电话和精确性都有积极的影响，以及（c）超过五千个关系实例是从500m级别的web for 66％的相关模型中获得的（III II）。探索这些类别的释义的常规基础，重点是日本光驱动构建体（LVC）的释义。我们为LVC提出了一个基于转换言语元素的词汇概念结构（LCS）的释义模型。我们还建议对现有LCS词典进行改进。实验结果表明，我们的基于LCS的释义模型表征了生成释义所需的那些动词的某些语义特征，例如动作的方向以及参数和表面案例之间的关系。较少的

项目成果

Acquiring Event Relation Knowledge by Learning Cooccurrence Patterns and Fertilizing Cooccurrence Samples with Verbal Nouns

• 发表时间: 2008
• 作者: Shuya Abe;Kentaro Inui;Yuji Matsumoto

「研究成果報告書概要(和文)」より

摘自《研究结果报告摘要（日文）》

• 发表时间: 2005
• 作者: Kawauchi;et. al.;Nishimura et al.;Dezawa et al.;Yoshizawa et al.;星野 幹雄;星野 幹雄
• 通讯作者: 星野 幹雄

Augmenting a Semantic Verb Lexicon with a Large Scale Collection of Example Sentences

用大量例句来扩充语义动词词典

• 发表时间: 2006
• 期刊: The 5th International Conference on Language Resources and Evaluation
• 作者: Kentaro Inui;Toru Hirano;Ryu Iida;Atsushi Fujita;Yuji Matsumoto
• 通讯作者: Yuji Matsumoto

Building a paraphrase corpus by class-oriented example sampling

通过面向类别的示例采样构建释义语料库

• 发表时间: 2006
• 期刊: Natural Language Processing Vol. 13, No. 3
• 作者: Atsushi;Fujita;Kentaro;Inui
• 通讯作者: Inui

A lexical semantic approach to computational modeling of paraphrase

释义计算建模的词汇语义方法

• 发表时间: 2006
• 期刊: Lexicon Forum Vol. 2
• 作者: Kentaro;Inui
• 通讯作者: Inui