Computation of Semantic Equivalence for Question Answering
Computation of Semantic Equivalence for Question Answering
复制标题
问答的语义等价计算
DOI：
10.1145/1135777.1135995
复制
发表时间：
2005
期刊：
影响因子：
3.5
通讯作者：
Tetsuro Takahashi
中科院分区：
文献类型：
--
作者：
Tetsuro Takahashi
在万维网、报刊杂志上有大量的文本数据。为了有效地访问这些文本数据，问题查询是一个选项。本文所使用的问句挖掘技术是指从大量的文本数据中为给定的用自然语言书写的问句寻找答案的技术。1999年开始的问题分类评估研讨会激励了许多研究人员改进这项任务的技术。本文提出了一种基于语义等价的问句生成方法，将问句生成问题看作是问句与文本之间语义等价的计算。本文提出了三个层次的语义等价评价方法：（1）利用文本的结构信息进行语义等价近似，（2）利用词汇结构变换进行语义等价评价，（3）利用抽取的语义关系进行语义等价评价。在第一级，我们进行了结构匹配作为一个近似的语义等价，而不是袋的词匹配，这是用于在以前的作品主要是问题分类。该方法是柯林斯树核的扩展，提供了三种相似性度量方法，并放宽了匹配的时间复杂度为O（|T1|| T2|).在第二个层次上，我们开发了一个日语词汇结构释义引擎Kura。我们还提出了一个问题的答案寻找算法，博士论文，信息处理部门，信息科学研究科，奈良科学技术研究所，NAIST-IS-DD 0261015，2005年2月3日。
There are vast amounts of text data on World Wide Web and in encyclopedias and newspapers. For efficient information access to such text data, Question Answering is an option. Question Answering which this thesis uses is defined that a technique to find an answer from a large amount of text data for a given question written in natural language. Evaluation workshops for Question Answering started in 1999 have motivated many researchers to improve techniques for the task. We take an approach to Question Answering task based on the semantic equivalence, regarding the problem of Question Answering as a computation of semantic equivalence between a question and text. We proposed evaluate methods of semantic equivalence in three levels, (1) approximation of semantic equivalence by structural information of text, (2) evaluation of semantic equivalence using lexico-structural transformation, (3) evaluation of semantic equivalence by extracted semantic relations. At the first level, we conducted structural matching as an approximation of semantic equivalence instead of bag-of-words matching which is utilized for Question Answering mainly in previous works. The proposed method, an extension of Collins’ Tree Kernel, provides three options for similarity measurement and relaxes the constraints of matching with the time complexity O(|T1||T2|). For the second level, we developed a Japanese lexico-structural paraphrasing engine called Kura. We also proposed an answer seeking algorithm for Question ∗Doctoral Dissertation, Department of Information Processing, Graduate School of Information Science, Nara Institute of Science and Technology, NAIST-IS-DD0261015, February 3, 2005.
DOI：
10.1007/10704656_11
发表时间：
1998-03
期刊：
--
影响因子：
--
作者：
Sergey Brin
通讯作者：
Sergey Brin