CASIA OpenIR  > 模式识别国家重点实验室  > 自然语言处理
Comparison Study on Critical Components in Composition Model for Phrase Representation
Wang, Shaonan1,2; Zong, Chengqing1,2,3
2017-04-01
发表期刊ACM TRANSACTIONS ON ASIAN AND LOW-RESOURCE LANGUAGE INFORMATION PROCESSING
卷号16期号:3页码:25
文章类型Article
摘要Phrase representation, an important step in many NLP tasks, involves representing phrases as continuousvalued vectors. This article presents detailed comparisons concerning the effects of word vectors, training data, and the composition and objective function used in a composition model for phrase representation. Specifically, we first discuss how the augmented word representations affect the performance of the composition model. Then, we investigate whether different types of training data influence the performance of the composition model and, if so, how they influence it. Finally, we evaluate combinations of different composition and objective functions and discuss the factors related to composition model performance. All evaluations were conducted in both English and Chinese. Our main findings are as follows: (1) The Additive model with semantic enhanced word vectors performs comparably to the state-of-the-art model; (2) The Additive model which updates augmented word vectors and the Matrix model with semantic enhanced word vectors systematically outperforms the state-of-the-art model in bigram and multi-word phrase similarity task, respectively; (3) Representing the high frequency phrases by estimating their surrounding contexts is a good training objective for bigram phrase similarity tasks; and (4) The performance gain of composition model with semantic enhanced word vectors is due to the composition function and the greater weight attached to important words. Previous works focus on the composition function; however, our findings indicate that other components in the composition model (especially word representation) make a critical difference in phrase representation.
关键词Phrase Representation Composition Model Retrofitting Word Paraphrasing Mean Square Error Max-margin
WOS标题词Science & Technology ; Technology
DOI10.1145/3010088
关键词[WOS]Phrase representation ; composition model ; retrofitting ; word paraphrasing ; mean square error ; max-margin
收录类别SCI
语种英语
项目资助者Natural Science Foundation of China(61333018) ; Strategic Priority Research Program of the CAS(XDB02070007)
WOS研究方向Computer Science
WOS类目Computer Science, Artificial Intelligence
WOS记录号WOS:000399087800002
引用统计
文献类型期刊论文
条目标识符http://ir.ia.ac.cn/handle/173211/15088
专题模式识别国家重点实验室_自然语言处理
作者单位1.National Laboratory of Pattern Recognition, Institute of Automation
2.University of Chinese Academy of Sciences
3.CAS Center for Excellence in Brain Science and Intelligence Technology
推荐引用方式
GB/T 7714
Wang, Shaonan,Zong, Chengqing. Comparison Study on Critical Components in Composition Model for Phrase Representation[J]. ACM TRANSACTIONS ON ASIAN AND LOW-RESOURCE LANGUAGE INFORMATION PROCESSING,2017,16(3):25.
APA Wang, Shaonan,&Zong, Chengqing.(2017).Comparison Study on Critical Components in Composition Model for Phrase Representation.ACM TRANSACTIONS ON ASIAN AND LOW-RESOURCE LANGUAGE INFORMATION PROCESSING,16(3),25.
MLA Wang, Shaonan,et al."Comparison Study on Critical Components in Composition Model for Phrase Representation".ACM TRANSACTIONS ON ASIAN AND LOW-RESOURCE LANGUAGE INFORMATION PROCESSING 16.3(2017):25.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
wangshaonan TALLPcom(516KB)期刊论文作者接受稿开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Wang, Shaonan]的文章
[Zong, Chengqing]的文章
百度学术
百度学术中相似的文章
[Wang, Shaonan]的文章
[Zong, Chengqing]的文章
必应学术
必应学术中相似的文章
[Wang, Shaonan]的文章
[Zong, Chengqing]的文章
相关权益政策
暂无数据
收藏/分享
文件名: wangshaonan TALLPcomparison study .pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。