Decomposable Neural Paraphrase Generation
This work addresses the need for interpretable and controllable paraphrase generation in natural language processing, though it is incremental as it builds on existing neural models.
The paper tackles the problem of generating paraphrases at different granularity levels by proposing a Transformer-based model with multiple encoders and decoders, achieving competitive in-domain performance and significantly better adaptation to new domains.
Paraphrasing exists at different granularity levels, such as lexical level, phrasal level and sentential level. This paper presents Decomposable Neural Paraphrase Generator (DNPG), a Transformer-based model that can learn and generate paraphrases of a sentence at different levels of granularity in a disentangled way. Specifically, the model is composed of multiple encoders and decoders with different structures, each of which corresponds to a specific granularity. The empirical study shows that the decomposition mechanism of DNPG makes paraphrase generation more interpretable and controllable. Based on DNPG, we further develop an unsupervised domain adaptation method for paraphrase generation. Experimental results show that the proposed model achieves competitive in-domain performance compared to the state-of-the-art neural models, and significantly better performance when adapting to a new domain.