[1]唐 琴,宋 锐,林鸿飞.基于Chunk-CRF的情感问答研究[J].智能系统学报,2008,3(06):504-510.
 TANG Qin,SONG Rui,LIN Hong-fei.Research on emotional question answering based on Chunk-CRF[J].CAAI Transactions on Intelligent Systems,2008,3(06):504-510.
点击复制

基于Chunk-CRF的情感问答研究(/HTML)
分享到:

《智能系统学报》[ISSN:1673-4785/CN:23-1538/TP]

卷:
第3卷
期数:
2008年06期
页码:
504-510
栏目:
出版日期:
2008-12-25

文章信息/Info

Title:
Research on emotional question answering based on Chunk-CRF
文章编号:
1673-4785(2008)06-0504-07
作者:
唐 琴宋 锐林鸿飞
大连理工大学计算机科学与工程系,辽宁大连116024
Author(s):
TANG Qin SONG Rui LIN Hong-fei
Department of Computer Science and Engineering, Dalian University of Technology, Dalian 116024,China
关键词:
事实性问答情感问答组块分析知网
Keywords:
factual question answering emotional QA Chunk-CRFHowNet
分类号:
TP391
文献标志码:
A
摘要:
相对于事实性问答系统而言,观点或情感问答系统的研究除了需要考虑观点持有者及情感倾向性等与情感相关问题以外,其难点还在于答案形式更复杂更分散.从百度知道人工搜集了大量的情感问题,并根据情感问题的特征,统计并归纳了五大情感问题类型.问题分类模式与传统事实性问答系统不同,不能仅仅根据疑问词对其进行分类,还需要考虑到观点以及受众的反应.问题分类使用基于Chunk的CRF模型与规则相结合的情感问题分类方法.在答案抽取时结合组块识别的结果和情感的倾向性,并根据情感问题类型的不同采取不同的方法以获取答案.实验结果表明了评价体系的有效性.
Abstract:
Emotional question answering analyses opinions, polarity, and other factors related to sentiment analysis. Evaluations are complex compared to those for responses to factual questions. A great number of emotional questions were collected from the internet, and a chunk conditional random field (CRF) model and heuristic rules were applied to classify them into five types based on the emotional features of the questions. This classification method is different from the factual question classification method, which is mainly based on interrogative words, as it has to take the opinions and responses from users into account. Combined with polarity and recognition results from Chunk-CRF, different answers were extracted according to different question types. The experiment shows that this evaluation system for emotional question answering is effective and efficient.

参考文献/References:

[1]CARDIE C, WIEBE J, LITMAN D, et al. Combining low-level and summary representations of opinions for multi-perspective question answering[C]//Proceedings of AAAI Spring Symposium Workshop.Stanford,Califonia,USA, 2003: 20-27.
[2]STOYANOV V, CARDIE C, WIEBE J. Multi-perspective questions answering using the OpQA corpus[C]//Proceedings of the Human Language Technology Conference and Conference on Empiricial Methods in Natural Language Processing. Vancouver, Canada, 2005: 923-930.
[3]YU H, HATZIVASSILOGLOU V. Towards answering opinion questions: separating facts from opinions and identifying the polarity of opinion sentences[C]//Proceedings of the 2003 Conference on Empirical Methods in Natural Language Processing. Sapporo, Japan, 2003: 129-136.
[4]SOMASUNDARAN S, WILSON T, WIEBE J, et al. QA with attitude: exploiting opinion type analysis for improving question answering in on-line discussions and the news[C]//Proceedings of the International Conference on Weblogs and Social Media. Boulder, Colorado,USA, 2007.
[5]KU Lunwei, LIANG Yuting, CHEN Hsinhsi. Question analysis and answer passage retrieval for opinion question answering systems[C]//Proceedings of 19th Conference on Computational Linguistics and Speech Processing. Taipei, China, 2007:177-190.
[6]CHKLOVSKI T. Deriving quantitative overviews of free text assessments on the web[C]// Proceedings of the 11th international conference on Intelligent User interfaces. New York, USA, 2006: 155-162.
[7]BAIDU. Baidu知道[EB/OL].[2008-05-02].http://zhidao.baidu.com.
[8]ABNEY S. Parsing by chunks[M]//BERWICK R, ABNEY S, TENNY C. Principle-Based Parsing. Dordrecht: Kluwer Academic Publishers, 1991.
[9]LAFFERTY J, MCCALLUM A, PEREIRA F. Conditional random fields: Probabilistic models for segmenting and labeling sequence data[C]//Proc 18th International Conf on Machine Learning. San Francisco, USA, 2001: 282-289.
[10]DONG Zhendong. HowNet knowledge datatase[EB/OL](2008-03-12).[2008-04-10].http://www.keenage.com/html/e_index.html.
[11]KRISHNAN V, DAS S, CHAKRABARTI S. Enhanced answer type inference from questions using sequential models[C]//Proceedings of Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing (HLT/EMNLP). Vancouver, Canada, 2005: 315-322.
[12]CoNLL 2000. Text chunking: A perl script for performance measuring [EB/OL]. [2008- 05- 01].http://www.cnts.ua.ac.be/conll2000/chunking/conlleval.txt.
[13]亚洲四小龙.周杰伦跟陈冠希哪个更帅[EB/OL]. [2008-04-15].http://zhidao.baidu.com/question/13834567.html?si=1.
[14]XUYING8763.大家最喜欢的港台的女明星是谁[EB/OL]. [2008- 04-15].http://zhidao.baidu.com/question/174674.html?si=1.〖ZK)〗

备注/Memo

备注/Memo:
收稿日期:2008-05-26.
基金项目:国家自然科学基金资助项目(60373095,60673039);国家863高科技计划资助项目(2006AA01Z151);教育部留学人员归国科研启动基金资助项目(教外司留[2007]1108).
作者简介:
唐    琴,女,1982年生,硕士研究生,主要研究方向为问答系统和自然语言处理.
宋    锐,男,1984年生,硕士研究生,主要研究方向为情感计算和自动文摘.
林鸿飞,男,1962生,教授,博士生导师,现任《中文信息学报》编委,中文信息学会理事,中国中文信息学会信息检索专业委员会委员,中国人工智能学会离散数学专业委员会副主任,中国人工智能学会机器学习专业委员会委员.主要研究方向为搜索引擎、文本挖掘、情感计算和自然语言理解.主持多项国家自然科学基金和863项目.发表学术论文100余篇.
更新日期/Last Update: 2009-04-03