logo
banner

Journals & Publications

Journals Publications Papers

Papers

Empirical Exploring Word-Character Relationship for Chinese Sentence Representation
Jul 11, 2018Author:
PrintText Size A A

Title: Empirical Exploring Word-Character Relationship for Chinese Sentence Representation

Authors: Wang, SN; Zhang, JJ; Zong, CQ

Author Full Names: Wang, Shaonan; Zhang, Jiajun; Zong, Chengqing

Source: ACM TRANSACTIONS ON ASIAN AND LOW-RESOURCE LANGUAGE INFORMATION PROCESSING, 17 (3):10.1145/3156778 MAY 2018

Language: English

Abstract: This article addresses the problem of learning compositional Chinese sentence representations, which represent the meaning of a sentence by composing the meanings of its constituent words. In contrast to English, a Chinese word is composed of characters, which contain rich semantic information. However, this information has not been fully exploited by existing methods. In this work, we introduce a novel, mixed character-word architecture to improve the Chinese sentence representations by utilizing rich semantic information of inner-word characters. We propose two novel strategies to reach this purpose. The first one is to use a mask gate on characters, learning the relation among characters in a word. The second one is to use a max-pooling operation on words to adaptively find the optimal mixture of the atomic and compositional word representations. Finally, the proposed architecture is applied to various sentence composition models, which achieves substantial performance gains over baseline models on sentence similarity task. To further verify the generalization ability of our model, we employ the learned sentence representations as features in sentence classification task, question classification task, and sentence entailment task. Results have shown that the proposed mixed character-word sentence representation models outperform both the character-based and word-based models.

ISSN: 2375-4699

eISSN: 2375-4702

Article Number: 14

IDS Number: GH0KL

Unique ID: WOS:000433090800001

*Click Here to View Full Record