不规则文本中商品名称识别的特征选择

计算机工程与科学

不规则文本中商品名称识别的特征选择

杨美妮1，何涛2，沈静1，张建军1

（1.海军工程大学理学院,湖北武汉 430033;2.中国科学院武汉文献情报中心,湖北武汉 430071）

收稿日期:2015-09-06 修回日期:2015-11-10 出版日期:2016-10-25 发布日期:2016-10-25
基金资助:
国家自然科学基金（61402516）

Feature selection for product name

recognition in informal texts

YANG Mei-ni1，HE Tao2，SHEN Jing1，ZHANG Jian-jun1

（1.College of Science,Naval University of Engineering,Wuhan 430033;

2.Wuhan Library of Chinese Academy of Sciences,Wuhan 430071,China）

Received:2015-09-06 Revised:2015-11-10 Online:2016-10-25 Published:2016-10-25

摘要/Abstract

摘要：

传统的命名实体识别任务多见于人名、地名、机构名这些普通的命名实体，且大多采用规则文本进行研究。随着电子商务和互联网广告的不断发展，如何从用户的各种不规则的上下文信息中自动识别出商品名称这一特殊的命名实体成为了一个需要解决的问题。为了解决这一问题，建立了一个最大熵模型用于识别论坛发帖这种不规则文本中的商品名称，并探讨了多种特征对于识别效果的影响。这些特征不仅包括传统命名实体识别方法中所使用的局部特征和布朗聚类特征，还包括词的分布式表示这种比较新颖的特征。这些特征按照各种不同的方式进行组合作为模型的输入。在CPROD01评测数据集上的实验结果表明，布朗聚类特征能够有效地提高商品名称识别系统的准确性。

关键词: 商品名称, 不规则文本, 最大熵模型, 词的分布式表示

Abstract:

Most previous studies on named entity recognition (NER) focus on common names such as persons,organizations,and locations in formal texts.With the development of e-commerce and online advertising,how to recognize product names which are special named entities in informal users context becomes more and more important.We design a maximum entropy model to recognize product names from forum posts and explore the impact of various features on the performance.These features include not only traditional features used for NER,but also distributed word representations which are novel ones obtained from the new area of machine learning.We compare the results of the experiments using different feature combinations as inputs.Experiments on the CPROD01 dataset show that the Brown cluster features can improve the accuracy of the product name recognition system.

Key words: product name, informal text, maximum entropy model, distributed representation of words

杨美妮1，何涛2，沈静1，张建军1. 不规则文本中商品名称识别的特征选择[J]. 计算机工程与科学.

YANG Mei-ni1，HE Tao2，SHEN Jing1，ZHANG Jian-jun1.

Feature selection for product name

recognition in informal texts

[J]. Computer Engineering & Science.

参考文献

［1］Grishman R,Sundheim B.Message understanding conference-6:A brief history［C］∥Proc of the 16th Conference on Computational Linguistics,1996:466-471.

［2］Zong Cheng-qing.Statistical natural language processing［M］.2nd Edition.Beijing:Tsinghua University Press,2013.(in Chinese)

［3］McCallum A,Li W.Early results for named entity recognition with conditional random fields,feature induction and web-enhanced lexicons［C］∥Proc of the 7th Conference on Natural Language Learning at HLT-NAACL,2003:188-191.

［4］Craven M,Kumlien J.Constructing biological knowledge bases by extracting information from text sources［C］∥Proc of the Intelligent Systems in Molecular Biology,1999:77-86.

［5］Bunescu R,Mooney R J.Relational Markov networks for collective information extraction［C］∥Proc of the ICML-2004 Workshop on Statistical Relational Learning and Its Connections to Other Fields,2004:1.

［6］Minkov E,Wang R C,Cohen W W.Extracting personal names from email:Applying named entity recognition to informal text［C］∥ Proc of the Conference on Human Language Technology and Empirical Methods in Natural Language Processing,2005:443-450.

［7］Ritter A,Clark S,Etzioni O.Named entity recognition in tweets:An experimental study［C］∥ Proc of the Conference on Empirical Methods in Natural Language Processing,2011:1524-1534.

［8］Tkachenko M,Simanovsky A.Named entity recognition:Exploring features［C］∥Proc of the Konvens,2012:118-127.

［9］Brown P F,Desouza P V,Mercer R L,et al.Class-based n-gram models of natural language［J］.Computational Linguistics,1992,18(4):467-479.

［10］Turian J, Ratinov L, Bengio Y.Word representations:A simple and general method for semi-supervised learning［C］∥ Proc of the 48th Annual Meeting of the Association for Computational Linguistics,2010:384-394.

［11］Hinton G E,Salakhutdinov R R.Reducing the dimensionality of data with neural networks［J］.Science,2006,313(5786):504-507.

［12］Berger A L,Pietra V J D,Pietra S A D.A maximum entropy approach to natural language processing［J］.Computational Linguistics,1996,22(1):39-71.

［13］Melli G,Romming C.An overview of the CPROD1 contest on consumer product recognition within user generated postings and normalization against a large product catalog［C］∥ Proc of the ICDM-2012 Workshop on Consumer Product Contest,2012:861-864.

［14］Hinton G E.Learning distributed representations of concepts［C］∥Proc of the 8th Annual Conference of the Cognitive Science Society,1986:1.

［15］Pennington J,Socher R,Manning C D.Glove:Global vectors for word representation［C］∥Proc of the Empirical Methods in Natural Language Processing,2014:1532-1543.

［16］Soricut R,Och F.Unsupervised morphology induction using word embeddings［C］∥ Proc of the 2015 Annual Conference of the North American Chapter of the ACL,2015:1627-1637.

［17］Collobert R,Weston J,Bottou L,et al.Natural language processing (almost) from scratch［J］.The Journal of Machine Learning Research,2011,12(4):2493-2537.

［18］Mnih A,Hinton G.Three new graphical models for statistical language modelling［C］∥ Proc of the 24th International Conference on Machine Learning,2007:641-648.

［19］Mnih A,Hinton G E.A scalable hierarchical distributed language model［C］∥ Proc of the Neural Information Processing Systems,2009:1081-1088.

［20］Li Hang.Statistical learning method ［M］.Beijing:Tsinghua University Press,2012.(in Chinese)

［21］Borthwick A.A maximum entropy approach to named entity recognition［D］.New York:New York University,1999.

［22］Lu Ming,Kang Yu-jie,Yu Neng-hai.Basic grammer rule and maximum entropy based hybrid model for name entity recognition ［J］.Journal of Chinese Computer Systems,2012,33(3):537-541.(in Chinese)

附中文参考文献：

［2］宗成庆.统计自然语言处理［M］.第2版.北京:清华大学出版社,2013.

［20］李航.统计学习方法［M］.北京:清华大学出版社,2012.

［22］陆铭,康雨洁,俞能海.简约语法规则和最大熵模型相结合的混合实体识别［J］.小型微型计算机系统,2012,33(3):537-541.

[1]	夏吾吉1,2，华却才让1. 基于投射的藏语语义依存分析研究[J]. 计算机工程与科学, 2019, 41(10): 1868-1873.
[2]	卢达威1，宋柔2. 基于最大熵模型的汉语标点句缺失话题自动识别初探[J]. J4, 2015, 37(12): 2282-2293.
[3]	才藏太. 基于最大熵分类器的藏文句子边界自动识别方法研究[J]. J4, 2012, 34(6): 187-190.
[4]	张晓艳王挺陈火旺. 基于混合统计模型的汉语命名实体识别方法[J]. J4, 2006, 28(6): 135-139.