{"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/character-based-neural-networks-for-sentence","title":"Character-based Neural Networks for Sentence Pair Modeling","arxiv_id":"1805.08297","date":"2018-05-21","proceeding":"NAACL 2018 6","authors":["Wuwei Lan","Wei Xu"],"abstract":"Sentence pair modeling is critical for many NLP tasks, such as paraphrase\nidentification, semantic textual similarity, and natural language inference.\nMost state-of-the-art neural models for these tasks rely on pretrained word\nembedding and compose sentence-level semantics in varied ways; however, few\nworks have attempted to verify whether we really need pretrained embeddings in\nthese tasks. In this paper, we study how effective subword-level (character and\ncharacter n-gram) representations are in sentence pair modeling. Though it is\nwell-known that subword models are effective in tasks with single sentence\ninput, including language modeling and machine translation, they have not been\nsystematically studied in sentence pair modeling tasks where the semantic and\nstring similarities between texts matter. Our experiments show that subword\nmodels without any pretrained word embedding can achieve new state-of-the-art\nresults on two social media datasets and competitive results on news data for\nparaphrase identification.","url_abs":"http://arxiv.org/abs/1805.08297v1","url_pdf":"http://arxiv.org/pdf/1805.08297v1.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":"character-based-neural-networks-for-sentence","repo_url":"https://github.com/lanwuwei/SPM_toolkit","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"natural-language-inference","task_name":"Natural Language Inference"},{"task_slug":"paraphrase-identification","task_name":"Paraphrase Identification"},{"task_slug":"semantic-textual-similarity","task_name":"Semantic Textual Similarity"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"sentence-pair-modeling","task_name":"Sentence Pair Modeling"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}