{"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/query-and-output-generating-words-by-querying","title":"Query and Output: Generating Words by Querying Distributed Word Representations for Paraphrase Generation","arxiv_id":"1803.01465","date":"2018-03-05","proceeding":"NAACL 2018 6","authors":["Shuming Ma","Xu sun","Wei Li","Sujian Li","Wenjie Li","Xuancheng Ren"],"abstract":"Most recent approaches use the sequence-to-sequence model for paraphrase\ngeneration. The existing sequence-to-sequence model tends to memorize the words\nand the patterns in the training dataset instead of learning the meaning of the\nwords. Therefore, the generated sentences are often grammatically correct but\nsemantically improper. In this work, we introduce a novel model based on the\nencoder-decoder framework, called Word Embedding Attention Network (WEAN). Our\nproposed model generates the words by querying distributed word representations\n(i.e. neural word embeddings), hoping to capturing the meaning of the according\nwords. Following previous work, we evaluate our model on two\nparaphrase-oriented tasks, namely text simplification and short text\nabstractive summarization. Experimental results show that our model outperforms\nthe sequence-to-sequence baseline by the BLEU score of 6.3 and 5.5 on two\nEnglish text simplification datasets, and the ROUGE-2 F1 score of 5.7 on a\nChinese summarization dataset. Moreover, our model achieves state-of-the-art\nperformances on these three benchmark datasets.","url_abs":"http://arxiv.org/abs/1803.01465v3","url_pdf":"http://arxiv.org/pdf/1803.01465v3.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":"query-and-output-generating-words-by-querying","repo_url":"https://github.com/lancopku/WEAN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"abstractive-text-summarization","task_name":"Abstractive Text Summarization"},{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"paraphrase-generation","task_name":"Paraphrase Generation"},{"task_slug":"text-simplification","task_name":"Text Simplification"},{"task_slug":"word-embeddings","task_name":"Word Embeddings"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1803.01465","atlas_url":"https://app.syntology.ai/?focus=1803.01465","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}