原创力文档- 1、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。。
- 2、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。
- 3、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)。
- 4、该文档为VIP文档，如果想要下载，成为VIP会员后，下载免费。
- 5、成为VIP后，下载本文档将扣除1次下载权益。下载后，不支持退款、换文档。如有疑问请联系我们。
- 6、成为VIP后，您将拥有八大权益，权益包括：VIP文档下载权益、阅读免打扰、文档格式转换、高级专利检索、专属身份标志、高级客服、多端互通、版权登记。
- 7、VIP文档为合作方或网友上传，每下载1次， 网站将根据用户上传文档的质量评分、类型等，对文档贡献者给予高额补贴、流量扶持。如果你也想贡献VIP文档。上传文档
查看更多
Automatic Retrieval and Clustering of Similar Words
Dekang Lin
Department of Computer Science
University of Manitoba
Winnipeg, Manitoba, Canada R 3 T 2N2
lindek@ cs.umanitoba.ca
Abstract the terms can be corpus- or genre-specific. Man-
Bootstrapping semantics from text is one of the ually constructed general-purpose dictionaries and
greatest challenges in natural language learning. thesauri include many usages that are very infre-
We first define a word similarity measure based on quent in a particular corpus or genre of documents.
the distributional pattern of words. The similarity For example, one of the 8 senses of company in
measure allows us to construct a thesaurus using a WordNet 1.5 is a visitor/visitant, which is a hy-
parsed corpus. We then present a new evaluation ponym of person. This usage of the word is prac-
methodology for the automatically constructed the- tically never used in newspaper articles. However,
saurus. The evaluation results show that the the- its existance may prevent a co-reference recognizer
saurns is significantly closer to WordNet than Roget to rule out the possiblity for personal pronouns to
Thesaurus is. refer to company. Secondly, certain word us-
ages may be particular to a period of time, which
1 Introduction
您可能关注的文档
- AN AGENT-BASED APPROACH FOR BUILDING COMPLEX SOFTWARE SYSTEMS -- WHY AGENT-ORIENTED APPROACHES ARE WELL SUITED FOR DEVELOPING COMPLEX, DISTRIBUTED SYSTEMS.：（一个基于代理的方法构建复杂的软件系统u2014u2014为什么AGENT-ORIENTED方法都适合开发复杂,分布式系统。）.pdf
- An algorithm for pronominal anaphora resolution：（一种算法对代词的重复法解决）.pdf
- An Algorithm that Learns What's in a Name：（一个算法学习有年代的一个名字）.pdf
- An Analysis of the Requirements Traceability Problem：（需求跟踪的分析问题）.pdf
- An Array-Based Algorithm for Simultaneous Multidimensional Aggregates：（一种基于阵列的同步算法多维聚合）.pdf
- An efficient algorithm for exploiting multiple arithmetic units：（一个高效的算法利用多个算术单元）.pdf
- An ecological perspective on health promotion programs：（生态的角度对健康促进计划）.pdf
- An Efficient Cryptographic Protocol Verifier Based on Prolog Rules：（一个高效的加密协议验证人基于Prolog规则）.pdf
- An Efficient Unification Algorithm：（一个有效的统一算法）.pdf
- An environmental energy harvesting framework for sensor networks：（为传感器网络环境能量收集框架）.pdf
- Automatic Abstraction without Counterexamples：（自动抽象没有反例）.pdf
- Basic Description Logics：（基本描述逻辑）.pdf
- Basic problems in stability and design of switched systems：（切换系统的稳定性和设计的基本问题）.pdf
- Biomedical named entity recognition using conditional random fields and rich feature sets：（生物命名实体识别使用条件随机域和丰富的功能集）.pdf
- Bottleneck flow control：（瓶颈流量控制）.pdf
- Building Diverse Computer Systems：（建立不同的计算机系统）.pdf
- By：（通过）.pdf
- C 1 Cli：（C 1 Cli）.pdf
- Capacity and Mutual Information of Wideband Multipath Fading Channels：（能力和宽带多径衰落信道的互信息）.pdf
- Capacity of Power Constrained Ad-Hoc Networks：（权力约束自组网能力）.pdf
文档评论（0）