{"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/sdnet-contextualized-attention-based-deep","title":"SDNet: Contextualized Attention-based Deep Network for Conversational Question Answering","arxiv_id":"1812.03593","date":"2018-12-10","proceeding":null,"authors":["Chenguang Zhu","Michael Zeng","Xuedong Huang"],"abstract":"Conversational question answering (CQA) is a novel QA task that requires\nunderstanding of dialogue context. Different from traditional single-turn\nmachine reading comprehension (MRC) tasks, CQA includes passage comprehension,\ncoreference resolution, and contextual understanding. In this paper, we propose\nan innovated contextualized attention-based deep neural network, SDNet, to fuse\ncontext into traditional MRC models. Our model leverages both inter-attention\nand self-attention to comprehend conversation context and extract relevant\ninformation from passage. Furthermore, we demonstrated a novel method to\nintegrate the latest BERT contextual model. Empirical results show the\neffectiveness of our model, which sets the new state of the art result in CoQA\nleaderboard, outperforming the previous best model by 1.6% F1. Our ensemble\nmodel further improves the result by 2.7% F1.","url_abs":"http://arxiv.org/abs/1812.03593v5","url_pdf":"http://arxiv.org/pdf/1812.03593v5.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":"sdnet-contextualized-attention-based-deep","repo_url":"https://github.com/Microsoft/SDNet","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"sdnet-contextualized-attention-based-deep","repo_url":"https://github.com/gooofy/zbrain","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"sdnet-contextualized-attention-based-deep","repo_url":"https://github.com/mpandeydev/SDnetmod","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"sdnet-contextualized-attention-based-deep","repo_url":"https://github.com/2023-MindSpore-1/ms-code-218/tree/main/sdne","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"sdnet-contextualized-attention-based-deep","repo_url":"https://github.com/2023-MindSpore-4/Code6/tree/main/SDNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null},{"paper_slug":"sdnet-contextualized-attention-based-deep","repo_url":"https://github.com/code-implementation1/Code7/tree/main/SDNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"conversational-question-answering","task_name":"Conversational Question Answering"},{"task_slug":"coreference-resolution","task_name":"Coreference Resolution"},{"task_slug":"machine-reading-comprehension","task_name":"Machine Reading Comprehension"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"reading-comprehension","task_name":"Reading Comprehension"},{"task_slug":"spoken-language-understanding","task_name":"Spoken Language Understanding"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bert","method_name":"BERT"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-linear-decay","method_name":"Linear Warmup With Linear Decay"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"},{"method_slug":"wordpiece","method_name":"WordPiece"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/question-answering-on-coqa","task":"Question Answering","dataset":"CoQA","model":"SDNet (ensemble)","rank_in_archive_order":8,"of":9,"metrics":{"Overall":"79.3"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-coqa","task":"Question Answering","dataset":"CoQA","model":"SDNet (single model)","rank_in_archive_order":9,"of":9,"metrics":{"Overall":"76.6"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1812.03593","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}