{"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/conversational-question-answering-on","title":"Conversational Question Answering on Heterogeneous Sources","arxiv_id":"2204.11677","date":"2022-04-25","proceeding":null,"authors":["Philipp Christmann","Rishiraj Saha Roy","Gerhard Weikum"],"abstract":"Conversational question answering (ConvQA) tackles sequential information needs where contexts in follow-up questions are left implicit. Current ConvQA systems operate over homogeneous sources of information: either a knowledge base (KB), or a text corpus, or a collection of tables. This paper addresses the novel issue of jointly tapping into all of these together, this way boosting answer coverage and confidence. We present CONVINSE, an end-to-end pipeline for ConvQA over heterogeneous sources, operating in three stages: i) learning an explicit structured representation of an incoming question and its conversational context, ii) harnessing this frame-like representation to uniformly capture relevant evidences from KB, text, and tables, and iii) running a fusion-in-decoder model to generate the answer. We construct and release the first benchmark, ConvMix, for ConvQA over heterogeneous sources, comprising 3000 real-user conversations with 16000 questions, along with entity annotations, completed question utterances, and question paraphrases. Experiments demonstrate the viability and advantages of our method, compared to state-of-the-art baselines.","url_abs":"https://arxiv.org/abs/2204.11677v2","url_pdf":"https://arxiv.org/pdf/2204.11677v2.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":"conversational-question-answering","task_name":"Conversational Question Answering"},{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"question-answering","task_name":"Question Answering"}],"methods":[{"method_slug":"base","method_name":"BASE"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/question-answering-on-timequestions","task":"Question Answering","dataset":"TimeQuestions","model":"Convinse","rank_in_archive_order":15,"of":21,"metrics":{"P@1":"42.3"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2204.11677","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}