发布求助
文献互助 智能选刊 最新文献

Proceedings of the 2003 conference on Empirical methods in natural language processing -最新文献

筛选
英文 中文
A General Framework for Distributional Similarity 分布相似度的一般框架
Proceedings of the 2003 conference on Empirical methods in natural language processing - Pub Date : 2003-07-11 DOI: 10.3115/1119355.1119366
Julie Weeds, David J. Weir
{"title":"A General Framework for Distributional Similarity","authors":"Julie Weeds, David J. Weir","doi":"10.3115/1119355.1119366","DOIUrl":"https://doi.org/10.3115/1119355.1119366","url":null,"abstract":"We present a general framework for distributional similarity based on the concepts of precision and recall. Different parameter settings within this framework approximate different existing similarity measures as well as many more which have, until now, been unexplored. We show that optimal parameter settings outperform two existing state-of-the-art similarity measures on two evaluation tasks for high and low frequency nouns.","PeriodicalId":428824,"journal":{"name":"Proceedings of the 2003 conference on Empirical methods in natural language processing -","volume":"277 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132738575","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 154
Evaluation and Extension of Maximum Entropy Models with Inequality Constraints 不等式约束下最大熵模型的评价与推广
Proceedings of the 2003 conference on Empirical methods in natural language processing - Pub Date : 2003-07-11 DOI: 10.3115/1119355.1119373
Jun'ichi Kazama, Junichi Tsujii
{"title":"Evaluation and Extension of Maximum Entropy Models with Inequality Constraints","authors":"Jun'ichi Kazama, Junichi Tsujii","doi":"10.3115/1119355.1119373","DOIUrl":"https://doi.org/10.3115/1119355.1119373","url":null,"abstract":"A maximum entropy (ME) model is usually estimated so that it conforms to equality constraints on feature expectations. However, the equality constraint is inappropriate for sparse and therefore unreliable features. This study explores an ME model with box-type inequality constraints, where the equality can be violated to reflect this unreliability. We evaluate the inequality ME model using text categorization datasets. We also propose an extension of the inequality ME model, which results in a natural integration with the Gaussian MAP estimation. Experimental results demonstrate the advantage of the inequality models and the proposed extension.","PeriodicalId":428824,"journal":{"name":"Proceedings of the 2003 conference on Empirical methods in natural language processing -","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114772387","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 124
HowtogetaChineseName(Entity): Segmentation and Combination Issues 如何组合tachinesename(实体):分割和组合问题
Proceedings of the 2003 conference on Empirical methods in natural language processing - Pub Date : 2003-07-11 DOI: 10.3115/1119355.1119381
Hongyan Jing, Radu Florian, Xiaoqiang Luo, Tong Zhang, Abraham Ittycheriah
{"title":"HowtogetaChineseName(Entity): Segmentation and Combination Issues","authors":"Hongyan Jing, Radu Florian, Xiaoqiang Luo, Tong Zhang, Abraham Ittycheriah","doi":"10.3115/1119355.1119381","DOIUrl":"https://doi.org/10.3115/1119355.1119381","url":null,"abstract":"When building a Chinese named entity recognition system, one must deal with certain language-specific issues such as whether the model should be based on characters or words. While there is no unique answer to this question, we discuss in detail advantages and disadvantages of each model, identify problems in segmentation and suggest possible solutions, presenting our observations, analysis, and experimental results. The second topic of this paper is classifier combination. We present and describe four classifiers for Chinese named entity recognition and describe various methods for combining their outputs. The results demonstrate that classifier combination is an effective technique of improving system performance: experiments over a large annotated corpus of fine-grained entity types exhibit a 10% relative reduction in F-measure error.","PeriodicalId":428824,"journal":{"name":"Proceedings of the 2003 conference on Empirical methods in natural language processing -","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122298110","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 31
Using LTAG Based Features in Parse Reranking 在解析重排序中使用基于LTAG的特征
Proceedings of the 2003 conference on Empirical methods in natural language processing - Pub Date : 2003-07-11 DOI: 10.3115/1119355.1119367
Libin Shen, Anoop Sarkar, A. Joshi
{"title":"Using LTAG Based Features in Parse Reranking","authors":"Libin Shen, Anoop Sarkar, A. Joshi","doi":"10.3115/1119355.1119367","DOIUrl":"https://doi.org/10.3115/1119355.1119367","url":null,"abstract":"We propose the use of Lexicalized Tree Adjoining Grammar (LTAG) as a source of features that are useful for reranking the output of a statistical parser. In this paper, we extend the notion of a tree kernel over arbitrary sub-trees of the parse to the derivation trees and derived trees provided by the LTAG formalism, and in addition, we extend the original definition of the tree kernel, making it more lexicalized and more compact. We use LTAG based features for the parse reranking task and obtain labeled recall and precision of 89.7%/90.0% on WSJ section 23 of Penn Treebank for sentences of length ≤ 100 words. Our results show that the use of LTAG based tree kernel gives rise to a 17% relative difference in f-score improvement over the use of a linear kernel without LTAG based features.","PeriodicalId":428824,"journal":{"name":"Proceedings of the 2003 conference on Empirical methods in natural language processing -","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125244326","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 66
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：604180095
Book学术官方微信