TREC 2003 Question Answering Track at CAS-ICT, Notebook of Text REtrieval Conference.pdf

下载文档

10
0
约1.5万字
约 5页
2017-04-11 发布于江苏
举报
版权申诉
保障服务

TREC 2003 Question Answering Track at CAS-ICT, Notebook of Text REtrieval Conference.pdf

1、本文档共5页，可阅读全部内容。
2、原创力文档（book118）网站文档一经付费（服务费），不意味着购买了该文档的版权，仅供个人/单位学习、研究之用，不得用于商业用途，未经授权，严禁复制、发行、汇编、翻译或者网络传播等，侵权必究。
3、本站所有内容均由合作方或网友上传，本站不对文档的完整性、权威性及其观点立场正确性做任何保证或承诺！文档内容仅供研究参考，付费前请自行鉴别。如您付费，意味着您自己接受本站规则且自行承担风险，本站不退款、不进行额外附加服务；查看《如何避免下载的几个坑》。如果您已付费下载过本站文档，您可以点击这里二次下载。
4、如文档侵犯商业秘密、侵犯著作权、侵犯人身权等，请点击“版权申诉”（推荐），也可以打举报电话：400-050-0827(电话支持时间：9:00-18:30)。

TREC 2003 Question Answering Track at CAS-ICT, Notebook of Text REtrieval Conference

TREC 2003 Question Answering Track at CAS-ICT Yi Chang, Hongbo Xu, Shuo Bai Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China {changyi, hbxu}@software.ict.ac.cn Abstract In our system, we make use of Chunk information to analyze the question. A multilevel method is fulfilled to retrieve candidate Bi-sentences. As to answer selecting, we proposed a voting method. We figure out the performance of each module of our system, and our study shows that 65.54% information has lost in document retrieval and Bi-sentence retrieval. Keyword: Chunk, Bi-sentence, multilevel retrieval, voting 1. Introduction It is the third time we take part in the TREC-QA track. We undertook the new main subtask and submitted three runs for evaluation. Our QA system incorporates several useful tools. The first is LT_CHUNK, which is developed at University of Edinburgh. We use LT_CHUNK to get the chunks of each sentence and the POS tags of different words. The second is GATE, developed by University of Sheffield. We use GATE to identify some Named Entities. In our previous QA system, we tried different kinds of elaborate algorithms, but the results were not satisfactory, and we didn’t make it clear what is the performance of each step in our system. So we try to figure it out this year, and our study shows: 65.54% information has lost in document retrieval and Bi-sentence retrieval. 2. System Description Our system contains four major modules, namely Question Analyzing Module, Multilevel Bi-sentence Retrieval Module, Entity Recognizing Module and Answer Selecting Module. However, for those definition questions, the Entity Recognizing Module is unnecessary. The system architecture is represented as below. To answer each question, Question Analyzing Module makes use of NLP techniques to identify the right type of information that the question requires. We select top 50 out of the 1000 given relevant documents to find the candidate answer