TransCouplet:Transformer based Chinese Couplet Generation
Kuan-Yu Chiang, Shihao Lin, Joe Chen, Qian Yin, Qizhen Jin
TL;DR
This paper introduces TransCouplet, a transformer-based model enhanced with ancient Chinese language understanding and grammatical rule evaluation for generating Chinese couplets effectively.
Contribution
It presents a novel transformer-based approach utilizing AnchiBERT and grammatical rule evaluation to improve Chinese couplet generation.
Findings
Enhanced generation quality with AnchiBERT integration
Improved grammatical accuracy through tagging methods
Effective handling of complex ancient Chinese syntax
Abstract
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.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsTopic Modeling · Natural Language Processing Techniques · Artificial Intelligence in Games