{"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/a-semantic-relevance-based-neural-network-for","title":"A Semantic Relevance Based Neural Network for Text Summarization and Text Simplification","arxiv_id":"1710.02318","date":"2017-10-06","proceeding":null,"authors":["Shuming Ma","Xu sun"],"abstract":"Text summarization and text simplification are two major ways to simplify the\ntext for poor readers, including children, non-native speakers, and the\nfunctionally illiterate. Text summarization is to produce a brief summary of\nthe main ideas of the text, while text simplification aims to reduce the\nlinguistic complexity of the text and retain the original meaning. Recently,\nmost approaches for text summarization and text simplification are based on the\nsequence-to-sequence model, which achieves much success in many text generation\ntasks. However, although the generated simplified texts are similar to source\ntexts literally, they have low semantic relevance. In this work, our goal is to\nimprove semantic relevance between source texts and simplified texts for text\nsummarization and text simplification. We introduce a Semantic Relevance Based\nneural model to encourage high semantic similarity between texts and summaries.\nIn our model, the source text is represented by a gated attention encoder,\nwhile the summary representation is produced by a decoder. Besides, the\nsimilarity score between the representations is maximized during training. Our\nexperiments show that the proposed model outperforms the state-of-the-art\nsystems on two benchmark corpus.","url_abs":"http://arxiv.org/abs/1710.02318v1","url_pdf":"http://arxiv.org/pdf/1710.02318v1.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":"a-semantic-relevance-based-neural-network-for","repo_url":"https://github.com/shumingma/SRB","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"semantic-similarity","task_name":"Semantic Similarity"},{"task_slug":"semantic-textual-similarity","task_name":"Semantic Textual Similarity"},{"task_slug":"text-generation","task_name":"Text Generation"},{"task_slug":"text-simplification","task_name":"Text Simplification"},{"task_slug":"text-summarization","task_name":"Text Summarization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}