{"type":"ScholarlyArticle","title":"Automatically Paraphrasing via Sentence Reconstruction and Round-trip Translation","authors":[{"name":"Zilu Guo","slug":"zilu-guo","given":"Zilu","family":"Guo","affiliation":""},{"name":"Zhongqiang Huang","slug":"zhongqiang-huang","given":"Zhongqiang","family":"Huang","affiliation":""},{"name":"Kenny Q. Zhu","slug":"kenny-q-zhu","given":"Kenny Q.","family":"Zhu","affiliation":""},{"name":"Guandan Chen","slug":"guandan-chen","given":"Guandan","family":"Chen","affiliation":""},{"name":"Kaibo Zhang","slug":"kaibo-zhang","given":"Kaibo","family":"Zhang","affiliation":""},{"name":"Boxing Chen","slug":"boxing-chen","given":"Boxing","family":"Chen","affiliation":""},{"name":"Fei Huang","slug":"fei-huang","given":"Fei","family":"Huang","affiliation":""}],"abstract":"Paraphrase generation plays key roles in NLP tasks such as question answering, machine translation, and information retrieval. In this paper, we propose a novel framework for paraphrase generation. It simultaneously decodes the output sentence using a pretrained wordset-to-sequence model and a round-trip translation model. We evaluate this framework on Quora, WikiAnswers, MSCOCO and Twitter, and show its advantage over previous state-of-the-art unsupervised methods and distantly-supervised methods by significant margins on all datasets. For Quora and WikiAnswers, our framework even performs better than some strongly supervised methods with domain adaptation. Further, we show that the generated paraphrases can be used to augment the training data for machine translation to achieve substantial improvements.","doi":"10.24963/ijcai.2021/525","url":"https://ijcai.org/proceedings/2021/525","pdf":"https://ijcai.org/proceedings/2021/0525.pdf","markdown":"https://ijcai.org/proceedings/2021/525.md","bibtex":"https://ijcai.org/proceedings/2021/bibtex/525","volume":{"slug":"2021","title":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2021","url":"https://ijcai.org/proceedings/2021/","year":2021,"location":"Montreal","dates":"19-27 August 2021","editors":"Prof. Zhi-Hua Zhou","isbn":"978-0-9992411-9-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2021"},"section":"Natural Language Processing","track":"Main Track","number":525,"pages":{"first":3815,"last":3821},"keywords":["Natural Language Processing: NLP Applications and Tools","Natural Language Processing: Natural Language Generation","Natural Language Processing: Machine Translation"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}