{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/neural-syntactic-preordering-for-controlled","title":"Neural Syntactic Preordering for Controlled Paraphrase Generation","arxiv_id":"2005.02013","date":"2020-05-05","proceeding":"ACL 2020 6","authors":["Tanya Goyal","Greg Durrett"],"abstract":"Paraphrasing natural language sentences is a multifaceted process: it might involve replacing individual words or short phrases, local rearrangement of content, or high-level restructuring like topicalization or passivization. Past approaches struggle to cover this space of paraphrase possibilities in an interpretable manner. Our work, inspired by pre-ordering literature in machine translation, uses syntactic transformations to softly \"reorder'' the source sentence and guide our neural paraphrasing model. First, given an input sentence, we derive a set of feasible syntactic rearrangements using an encoder-decoder model. This model operates over a partially lexical, partially syntactic view of the sentence and can reorder big chunks. Next, we use each proposed rearrangement to produce a sequence of position embeddings, which encourages our final encoder-decoder paraphrase model to attend to the source words in a particular order. Our evaluation, both automatic and human, shows that the proposed system retains the quality of the baseline approaches while giving a substantial increase in the diversity of the generated paraphrases","url_abs":"https://arxiv.org/abs/2005.02013v1","url_pdf":"https://arxiv.org/pdf/2005.02013v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"neural-syntactic-preordering-for-controlled","repo_url":"https://github.com/tagoyal/sow-reap-paraphrasing","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"neural-syntactic-preordering-for-controlled","repo_url":"https://github.com/bengittelson/sow-reap-paraphrasing","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"paraphrase-generation","task_name":"Paraphrase Generation"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2005.02013","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}