{"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/explainable-conversational-question-answering","title":"Explainable Conversational Question Answering over Heterogeneous Sources via Iterative Graph Neural Networks","arxiv_id":"2305.01548","date":"2023-05-02","proceeding":null,"authors":["Philipp Christmann","Rishiraj Saha Roy","Gerhard Weikum"],"abstract":"In conversational question answering, users express their information needs through a series of utterances with incomplete context. Typical ConvQA methods rely on a single source (a knowledge base (KB), or a text corpus, or a set of tables), thus being unable to benefit from increased answer coverage and redundancy of multiple sources. Our method EXPLAIGNN overcomes these limitations by integrating information from a mixture of sources with user-comprehensible explanations for answers. It constructs a heterogeneous graph from entities and evidence snippets retrieved from a KB, a text corpus, web tables, and infoboxes. This large graph is then iteratively reduced via graph neural networks that incorporate question-level attention, until the best answers and their explanations are distilled. Experiments show that EXPLAIGNN improves performance over state-of-the-art baselines. A user study demonstrates that derived answers are understandable by end users.","url_abs":"https://arxiv.org/abs/2305.01548v2","url_pdf":"https://arxiv.org/pdf/2305.01548v2.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":"explainable-conversational-question-answering","repo_url":"https://github.com/philippchr/explaignn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"conversational-question-answering","task_name":"Conversational Question Answering"},{"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-tiq","task":"Question Answering","dataset":"TIQ","model":"Explaignn","rank_in_archive_order":2,"of":9,"metrics":{"P@1":"44.6"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-timequestions","task":"Question Answering","dataset":"TimeQuestions","model":"EXPLAIGNN","rank_in_archive_order":9,"of":21,"metrics":{"P@1":"52.5"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2305.01548","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}