{"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/sentence-similarity-learning-by-lexical","title":"Sentence Similarity Learning by Lexical Decomposition and Composition","arxiv_id":"1602.07019","date":"2016-02-23","proceeding":"COLING 2016 12","authors":["Zhiguo Wang","Haitao Mi","Abraham Ittycheriah"],"abstract":"Most conventional sentence similarity methods only focus on similar parts of\ntwo input sentences, and simply ignore the dissimilar parts, which usually give\nus some clues and semantic meanings about the sentences. In this work, we\npropose a model to take into account both the similarities and dissimilarities\nby decomposing and composing lexical semantics over sentences. The model\nrepresents each word as a vector, and calculates a semantic matching vector for\neach word based on all words in the other sentence. Then, each word vector is\ndecomposed into a similar component and a dissimilar component based on the\nsemantic matching vector. After this, a two-channel CNN model is employed to\ncapture features by composing the similar and dissimilar components. Finally, a\nsimilarity score is estimated over the composed feature vectors. Experimental\nresults show that our model gets the state-of-the-art performance on the answer\nsentence selection task, and achieves a comparable result on the paraphrase\nidentification task.","url_abs":"http://arxiv.org/abs/1602.07019v2","url_pdf":"http://arxiv.org/pdf/1602.07019v2.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":"sentence-similarity-learning-by-lexical","repo_url":"https://github.com/Leputa/CIKM-AnalytiCup-2018","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"paraphrase-identification","task_name":"Paraphrase Identification"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"sentence-similarity","task_name":"Sentence Similarity"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/question-answering-on-wikiqa","task":"Question Answering","dataset":"WikiQA","model":"LDC","rank_in_archive_order":13,"of":25,"metrics":{"MAP":"0.7058","MRR":"0.7226"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1602.07019","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}