{"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/neural-paraphrase-identification-of-questions","title":"Neural Paraphrase Identification of Questions with Noisy Pretraining","arxiv_id":"1704.04565","date":"2017-04-15","proceeding":"WS 2017 9","authors":["Gaurav Singh Tomar","Thyago Duque","Oscar Täckström","Jakob Uszkoreit","Dipanjan Das"],"abstract":"We present a solution to the problem of paraphrase identification of\nquestions. We focus on a recent dataset of question pairs annotated with binary\nparaphrase labels and show that a variant of the decomposable attention model\n(Parikh et al., 2016) results in accurate performance on this task, while being\nfar simpler than many competing neural architectures. Furthermore, when the\nmodel is pretrained on a noisy dataset of automatically collected question\nparaphrases, it obtains the best reported performance on the dataset.","url_abs":"http://arxiv.org/abs/1704.04565v2","url_pdf":"http://arxiv.org/pdf/1704.04565v2.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":[],"tasks":[{"task_slug":"paraphrase-identification","task_name":"Paraphrase Identification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/paraphrase-identification-on-quora-question","task":"Paraphrase Identification","dataset":"Quora Question Pairs","model":"pt-DecAtt","rank_in_archive_order":23,"of":31,"metrics":{"Accuracy":"88.40"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1704.04565","atlas_url":"https://app.syntology.ai/?focus=1704.04565","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}