Negative lexically constrained decoding for paraphrase generation

Abstract

Paraphrase generation can be regarded as monolingual translation. Unlike bilingual machine translation, paraphrase generation rewrites only a limited portion of an input sentence. Hence, previous methods based on machine translation often perform conservatively to fail to make necessary rewrites. To solve this problem, we propose a neural model for paraphrase generation that first identifies words in the source sentence that should be paraphrased. Then, these words are paraphrased by the negative lexically constrained decoding that avoids outputting these words as they are. Experiments on text simplification and formality transfer show that our model improves the quality of paraphrasing by making necessary rewrites to an input sentence.

Publication
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (ACL 2019)
Tomoyuki Kajiwara
Tomoyuki Kajiwara
Guest Assistant Professor

Natural Language Processing. Especially: Text Simplification, Paraphrasing, Semantic Textual Similarity, Quality Estimation.