TransCouplet:Transformer based Chinese Couplet Generation
This work addresses the problem of automated poetry creation for applications in cultural preservation and natural language processing, representing an incremental advancement in domain-specific methods.
The paper tackled the challenge of generating Chinese couplets, which involve complex syntax and ancient language, by developing a transformer-based sequence-to-sequence model that incorporates AnchiBERT for language understanding and evaluates glyph, pinyin, and part-of-speech tagging to enhance grammatical rules, resulting in improved couplet generation.
Chinese couplet is a special form of poetry composed of complex syntax with ancient Chinese language. Due to the complexity of semantic and grammatical rules, creation of a suitable couplet is a formidable challenge. This paper presents a transformer-based sequence-to-sequence couplet generation model. With the utilization of AnchiBERT, the model is able to capture ancient Chinese language understanding. Moreover, we evaluate the Glyph, PinYin and Part-of-Speech tagging on the couplet grammatical rules to further improve the model.