{"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/m2s-net-multi-modal-similarity-metric","title":"M$^2$S-Net: Multi-Modal Similarity Metric Learning based Deep Convolutional Network for Answer Selection","arxiv_id":"1604.05519","date":"2016-04-19","proceeding":null,"authors":["Lingxun Meng","Yan Li"],"abstract":"Recent works using artificial neural networks based on distributed word\nrepresentation greatly boost performance on various natural language processing\ntasks, especially the answer selection problem. Nevertheless, most of the\nprevious works used deep learning methods (like LSTM-RNN, CNN, etc.) only to\ncapture semantic representation of each sentence separately, without\nconsidering the interdependence between each other. In this paper, we propose a\nnovel end-to-end learning framework which constitutes deep convolutional neural\nnetwork based on multi-modal similarity metric learning (M$^2$S-Net) on\npairwise tokens. The proposed model demonstrates its performance by surpassing\nprevious state-of-the-art systems on the answer selection benchmark, i.e.,\nTREC-QA dataset, in both MAP and MRR metrics.","url_abs":"http://arxiv.org/abs/1604.05519v3","url_pdf":"http://arxiv.org/pdf/1604.05519v3.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":"m2s-net-multi-modal-similarity-metric","repo_url":"https://github.com/lxmeng/mms_answer_selection","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"answer-selection","task_name":"Answer Selection"},{"task_slug":"metric-learning","task_name":"Metric Learning"},{"task_slug":"sentence","task_name":"Sentence"}],"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}