{"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/look-before-you-hop-conversational-question","title":"Look before you Hop: Conversational Question Answering over Knowledge Graphs Using Judicious Context Expansion","arxiv_id":"1910.03262","date":"2019-10-08","proceeding":null,"authors":["Philipp Christmann","Rishiraj Saha Roy","Abdalghani Abujabal","Jyotsna Singh","Gerhard Weikum"],"abstract":"Fact-centric information needs are rarely one-shot; users typically ask follow-up questions to explore a topic. In such a conversational setting, the user's inputs are often incomplete, with entities or predicates left out, and ungrammatical phrases. This poses a huge challenge to question answering (QA) systems that typically rely on cues in full-fledged interrogative sentences. As a solution, we develop CONVEX: an unsupervised method that can answer incomplete questions over a knowledge graph (KG) by maintaining conversation context using entities and predicates seen so far and automatically inferring missing or ambiguous pieces for follow-up questions. The core of our method is a graph exploration algorithm that judiciously expands a frontier to find candidate answers for the current question. To evaluate CONVEX, we release ConvQuestions, a crowdsourced benchmark with 11,200 distinct conversations from five different domains. We show that CONVEX: (i) adds conversational support to any stand-alone QA system, and (ii) outperforms state-of-the-art baselines and question completion strategies.","url_abs":"https://arxiv.org/abs/1910.03262v3","url_pdf":"https://arxiv.org/pdf/1910.03262v3.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":"look-before-you-hop-conversational-question","repo_url":"https://github.com/PhilippChr/CONVEX","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"conversational-question-answering","task_name":"Conversational Question Answering"},{"task_slug":"knowledge-graphs","task_name":"Knowledge Graphs"},{"task_slug":"question-answering","task_name":"Question Answering"}],"methods":[],"datasets_introduced":[{"slug":"convquestions","name":"ConvQuestions","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1910.03262","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.03262"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/PhilippChr/CONVEX","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":7},"by_repo_kind":{"official":{"samples":7,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"a050b095f878d0cb","entry":"expand_context_with_candidates","repo":"PhilippChr/CONVEX","repo_kind":"official","path":"library/graph_processing.py","file_url":"https://github.com/PhilippChr/CONVEX/blob/HEAD/library/graph_processing.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a050b095f878d0cb"}},{"code_sha256_prefix":"c8f7e81f1543afe7","entry":"expand_context_with_frontier","repo":"PhilippChr/CONVEX","repo_kind":"official","path":"library/graph_processing.py","file_url":"https://github.com/PhilippChr/CONVEX/blob/HEAD/library/graph_processing.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c8f7e81f1543afe7"}},{"code_sha256_prefix":"fc12a674d6d1c0b0","entry":"expand_context_with_statements","repo":"PhilippChr/CONVEX","repo_kind":"official","path":"library/graph_processing.py","file_url":"https://github.com/PhilippChr/CONVEX/blob/HEAD/library/graph_processing.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fc12a674d6d1c0b0"}},{"code_sha256_prefix":"c6f148510f597285","entry":"is_entity_or_literal","repo":"PhilippChr/CONVEX","repo_kind":"official","path":"library/wikidata.py","file_url":"https://github.com/PhilippChr/CONVEX/blob/HEAD/library/wikidata.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c6f148510f597285"}},{"code_sha256_prefix":"e551353ebb702dc5","entry":"is_literal_or_date","repo":"PhilippChr/CONVEX","repo_kind":"official","path":"library/string_conversions.py","file_url":"https://github.com/PhilippChr/CONVEX/blob/HEAD/library/string_conversions.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e551353ebb702dc5"}},{"code_sha256_prefix":"5b216a411c982687","entry":"parse_answers","repo":"PhilippChr/CONVEX","repo_kind":"official","path":"library/string_conversions.py","file_url":"https://github.com/PhilippChr/CONVEX/blob/HEAD/library/string_conversions.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5b216a411c982687"}},{"code_sha256_prefix":"c26e9b6844f1c84b","entry":"wikidata_url_to_wikidata_id","repo":"PhilippChr/CONVEX","repo_kind":"official","path":"library/string_conversions.py","file_url":"https://github.com/PhilippChr/CONVEX/blob/HEAD/library/string_conversions.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c26e9b6844f1c84b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}