Chinese Couplet Generation with Neural Network Structures
40249Authors
nan
Abstract
Part of the unique cultural heritage of Chi- na is the Chinese couplet. Given a sen- tence (namely an antecedent clause), peo- ple reply with another sentence (namely a subsequent clause) equal in length. More- over, a special phenomenon is that corre- sponding characters from the same posi- tion in the two clauses match each oth- er by following certain constraints on se- mantic and/or syntactic relatedness. Au- tomatic 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 anteceden- t clause, the system generates the subse- quent clause via sequential language mod- eling. 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 iterative- ly. A comprehensive evaluation, using per- plexity and BLEU measurements as well as human judgments, has demonstrated the effectiveness of our proposed approach. 1
Keywords
Full Content
Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, pages 2347–2357, Berlin, Germany, August 7-12, 2016. c⃝2016 Association for Computational Linguistics Chinese Couplet Generation with Neural Network Structures Rui Yan1,2, Cheng-Te Li3, Xiaohua Hu4, and Ming Zhang5 1Institute of Computer Science and Technology, Peking University, Beijing 100871, China 2Natural Language Processing Department, Baidu Inc., Beijing 100193, China 3Academia Sinica, Taipei 11529, Taiwan 4College of Computing and Informatics, Drexel University, Philadelphia, PA 19104, USA 5Department of Computer Science, Peking University, Beijing 100871, China yanrui02@baidu.com, ctli@citi.sinica.edu.tw xh29@drexel.edu, mzhang cs@pku.edu.cn Abstract Part of the unique cultural heritage of Chi- na is the Chinese couplet. Given a sen- tence (namely an antecedent clause), peo- ple reply with another sentence (namely a subsequent clause) equal in length. More- over, a special phenomenon is that corre- sponding characters from the same posi- tion in the two clauses match each oth- er by following certain constraints on se- mantic and/or syntactic relatedness. Au- tomatic 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 anteceden- t clause, the system generates the subse- quent clause via sequential language mod- eling. 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 iterative- ly. A comprehensive evaluation, using per- plexity and BLEU measurements as well as human judgments, has demonstrated the effectiveness of our proposed approach. 1 Introduction Chinese antithetical couplets, (namely “对联”), form a special type of poetry composed of two clauses (i.e., sentences). The popularity of the game of Chinese couplet challenge manifests itself in many aspects of people’s life, e.g., as a mean- s of expressing personal emotion, political views, or communicating messages at festive occasions. Hence, Chinese couplets are considered an impor- tant cultural heritage. A couplet is often written in calligraphy on red banners during special oc- casions such as wedding ceremonies and the Chi- nese New Year. People also use couplets to cele- brate birthdays, mark the openings of a business, and commemorate historical events. We illustrate a real couplet for Chinese New Year celebration in Figure 1, and translate the couplet into English character-by-character. Usually in the couplet generation game, one person challenges the other person with a sentence (namely an antecedent clause). The other person then replies with another sentence (namely a sub- sequent clause) equal in length and term segmen- tation, in a way that corresponding characters from the same position in the two clauses match each other by obeying certain constraints on semantic and/or syntactic relatedness. We also illustrate the special phenomenon of Chinese couplet in Figure 1: “one” is paired with “two”, “term” is associat- ed with “character”, “hundred” is mapped into “t- housand”, and “happiness” is coupled with “trea- sures”. As opposed to free languages, couplets have unique poetic elegance, e.g., aestheticism and conciseness etc. …
Content truncated to 500 words
Labeled Text
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. 1
Publication Details
- Paper ID:
- 40249
- Year:
- 2016
- Publication:
- TIPSTER
- Publication Type:
- conf
- DOI:
- nan