{"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/integrating-transformer-and-paraphrase-rules","title":"Integrating Transformer and Paraphrase Rules for Sentence Simplification","arxiv_id":"1810.11193","date":"2018-10-26","proceeding":"EMNLP 2018 10","authors":["Sanqiang Zhao","Rui Meng","Daqing He","Saptono Andi","Parmanto Bambang"],"abstract":"Sentence simplification aims to reduce the complexity of a sentence while\nretaining its original meaning. Current models for sentence simplification\nadopted ideas from ma- chine translation studies and implicitly learned\nsimplification mapping rules from normal- simple sentence pairs. In this paper,\nwe explore a novel model based on a multi-layer and multi-head attention\narchitecture and we pro- pose two innovative approaches to integrate the Simple\nPPDB (A Paraphrase Database for Simplification), an external paraphrase\nknowledge base for simplification that covers a wide range of real-world\nsimplification rules. The experiments show that the integration provides two\nmajor benefits: (1) the integrated model outperforms multiple state- of-the-art\nbaseline models for sentence simplification in the literature (2) through\nanalysis of the rule utilization, the model seeks to select more accurate\nsimplification rules. The code and models used in the paper are available at\nhttps://github.com/ Sanqiang/text_simplification.","url_abs":"http://arxiv.org/abs/1810.11193v1","url_pdf":"http://arxiv.org/pdf/1810.11193v1.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":"integrating-transformer-and-paraphrase-rules","repo_url":"https://github.com/Sanqiang/text_simplification","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"text-simplification","task_name":"Text Simplification"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/text-simplification-on-asset","task":"Text Simplification","dataset":"ASSET","model":"DMASS-DCSS","rank_in_archive_order":7,"of":12,"metrics":{"BLEU":"71.44*","SARI (EASSE>=0.2.1)":"38.67"},"uses_additional_data":false},{"leaderboard":"/sota/text-simplification-on-newsela","task":"Text Simplification","dataset":"Newsela","model":"DMASS + DCSS","rank_in_archive_order":9,"of":13,"metrics":{"SARI":"27.28"},"uses_additional_data":false},{"leaderboard":"/sota/text-simplification-on-turkcorpus","task":"Text Simplification","dataset":"TurkCorpus","model":"DMASS-DCSS","rank_in_archive_order":7,"of":25,"metrics":{"SARI (EASSE>=0.2.1)":"40.45"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1810.11193","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}