Automatic Acrostic Couplet Generation with Three-Stage Neural Network Pipelines
Autor: | Bojin Zhuang, Shaojun Wang, Xiao Jing, Haoshen Fan, Wang Jie |
---|---|
Rok vydání: | 2019 |
Předmět: |
Artificial neural network
Computer science business.industry Natural language generation 020206 networking & telecommunications 02 engineering and technology computer.software_genre 01 natural sciences Pipeline (software) Field (computer science) Antecedent (grammar) TheoryofComputation_MATHEMATICALLOGICANDFORMALLANGUAGES 0103 physical sciences 0202 electrical engineering electronic engineering information engineering Beam search Language model Artificial intelligence Couplet business 010301 acoustics computer Natural language processing |
Zdroj: | PRICAI 2019: Trends in Artificial Intelligence ISBN: 9783030299071 PRICAI (1) |
Popis: | As one of the quintessence of Chinese traditional culture, couplet compromises two syntactically symmetric clauses equal in length, namely, an antecedent and subsequent clause. Moreover, corresponding characters and phrases at the same position of the two clauses are paired with each other under certain constraints of semantic and/or syntactic relatedness. Automatic couplet generation is recognized as a challenging problem even in the Artificial Intelligence field. In this paper, we comprehensively study on automatic generation of acrostic couplet with the first characters defined by users. The complete couplet generation is mainly divided into three stages, that is, antecedent clause generation pipeline, subsequent clause generation pipeline and clause re-ranker. To realize semantic and/or syntactic relatedness between two clauses, attention-based Sequence-to-Sequence (S2S) neural network is employed. Moreover, to provide diverse couplet candidates for re-ranking, a cluster-based beam search approach is incorporated into the S2S network. Both BLEU metrics and human judgments have demonstrated the effectiveness of our proposed method. Eventually, a mini-program based on this generation system is developed and deployed on Wechat for real users. |
Databáze: | OpenAIRE |
Externí odkaz: |