Chinese couplet generation with neural network structures

Rui Yan, Cheng-Te Li, Xiaohua Hu, Ming Zhang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

6 Citations (Scopus)

Abstract

Part of the unique cultural heritage of China is the Chinese couplet. Given a sentence (namely an antecedent clause), people reply with another sentence (namely a subsequent clause) equal in length. Moreover, a special phenomenon is that corresponding characters from the same position in the two clauses match each other by following certain constraints on semantic and/or syntactic relatedness. Automatic couplet generation by computer is viewed as a difficult problem and has not been fully explored. In this paper, we formulate the task as a natural language generation problem using neural network structures. Given the issued antecedent clause, the system generates the subsequent clause via sequential language modeling. To satisfy special characteristics of couplets, we incorporate the attention mechanism and polishing schema into the encoding-decoding process. The couplet is generated incrementally and iteratively. A comprehensive evaluation, using perplexity and BLEU measurements as well as human judgments, has demonstrated the effectiveness of our proposed approach.

Original languageEnglish
Title of host publication54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Long Papers
PublisherAssociation for Computational Linguistics (ACL)
Pages2347-2357
Number of pages11
ISBN (Electronic)9781510827585
Publication statusPublished - 2016 Jan 1
Event54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Berlin, Germany
Duration: 2016 Aug 72016 Aug 12

Publication series

Name54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Long Papers
Volume4

Other

Other54th Annual Meeting of the Association for Computational Linguistics, ACL 2016
CountryGermany
CityBerlin
Period16-08-0716-08-12

Fingerprint

neural network
language
cultural heritage
semantics
China
evaluation
Couplet
Neural Networks
Clause

All Science Journal Classification (ASJC) codes

  • Language and Linguistics
  • Linguistics and Language

Cite this

Yan, R., Li, C-T., Hu, X., & Zhang, M. (2016). Chinese couplet generation with neural network structures. In 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Long Papers (pp. 2347-2357). (54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Long Papers; Vol. 4). Association for Computational Linguistics (ACL).
Yan, Rui ; Li, Cheng-Te ; Hu, Xiaohua ; Zhang, Ming. / Chinese couplet generation with neural network structures. 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Long Papers. Association for Computational Linguistics (ACL), 2016. pp. 2347-2357 (54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Long Papers).
@inproceedings{23cc398825514806807254dfc536411b,
title = "Chinese couplet generation with neural network structures",
abstract = "Part of the unique cultural heritage of China is the Chinese couplet. Given a sentence (namely an antecedent clause), people reply with another sentence (namely a subsequent clause) equal in length. Moreover, a special phenomenon is that corresponding characters from the same position in the two clauses match each other by following certain constraints on semantic and/or syntactic relatedness. Automatic couplet generation by computer is viewed as a difficult problem and has not been fully explored. In this paper, we formulate the task as a natural language generation problem using neural network structures. Given the issued antecedent clause, the system generates the subsequent clause via sequential language modeling. To satisfy special characteristics of couplets, we incorporate the attention mechanism and polishing schema into the encoding-decoding process. The couplet is generated incrementally and iteratively. A comprehensive evaluation, using perplexity and BLEU measurements as well as human judgments, has demonstrated the effectiveness of our proposed approach.",
author = "Rui Yan and Cheng-Te Li and Xiaohua Hu and Ming Zhang",
year = "2016",
month = "1",
day = "1",
language = "English",
series = "54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Long Papers",
publisher = "Association for Computational Linguistics (ACL)",
pages = "2347--2357",
booktitle = "54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Long Papers",

}

Yan, R, Li, C-T, Hu, X & Zhang, M 2016, Chinese couplet generation with neural network structures. in 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Long Papers. 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Long Papers, vol. 4, Association for Computational Linguistics (ACL), pp. 2347-2357, 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016, Berlin, Germany, 16-08-07.

Chinese couplet generation with neural network structures. / Yan, Rui; Li, Cheng-Te; Hu, Xiaohua; Zhang, Ming.

54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Long Papers. Association for Computational Linguistics (ACL), 2016. p. 2347-2357 (54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Long Papers; Vol. 4).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Chinese couplet generation with neural network structures

AU - Yan, Rui

AU - Li, Cheng-Te

AU - Hu, Xiaohua

AU - Zhang, Ming

PY - 2016/1/1

Y1 - 2016/1/1

N2 - Part of the unique cultural heritage of China is the Chinese couplet. Given a sentence (namely an antecedent clause), people reply with another sentence (namely a subsequent clause) equal in length. Moreover, a special phenomenon is that corresponding characters from the same position in the two clauses match each other by following certain constraints on semantic and/or syntactic relatedness. Automatic couplet generation by computer is viewed as a difficult problem and has not been fully explored. In this paper, we formulate the task as a natural language generation problem using neural network structures. Given the issued antecedent clause, the system generates the subsequent clause via sequential language modeling. To satisfy special characteristics of couplets, we incorporate the attention mechanism and polishing schema into the encoding-decoding process. The couplet is generated incrementally and iteratively. A comprehensive evaluation, using perplexity and BLEU measurements as well as human judgments, has demonstrated the effectiveness of our proposed approach.

AB - Part of the unique cultural heritage of China is the Chinese couplet. Given a sentence (namely an antecedent clause), people reply with another sentence (namely a subsequent clause) equal in length. Moreover, a special phenomenon is that corresponding characters from the same position in the two clauses match each other by following certain constraints on semantic and/or syntactic relatedness. Automatic couplet generation by computer is viewed as a difficult problem and has not been fully explored. In this paper, we formulate the task as a natural language generation problem using neural network structures. Given the issued antecedent clause, the system generates the subsequent clause via sequential language modeling. To satisfy special characteristics of couplets, we incorporate the attention mechanism and polishing schema into the encoding-decoding process. The couplet is generated incrementally and iteratively. A comprehensive evaluation, using perplexity and BLEU measurements as well as human judgments, has demonstrated the effectiveness of our proposed approach.

UR - http://www.scopus.com/inward/record.url?scp=85011982262&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85011982262&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85011982262

T3 - 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Long Papers

SP - 2347

EP - 2357

BT - 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Long Papers

PB - Association for Computational Linguistics (ACL)

ER -

Yan R, Li C-T, Hu X, Zhang M. Chinese couplet generation with neural network structures. In 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Long Papers. Association for Computational Linguistics (ACL). 2016. p. 2347-2357. (54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Long Papers).