{"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/question-decomposition-with-dependency-graphs","title":"Question Decomposition with Dependency Graphs","arxiv_id":"2104.08647","date":"2021-04-17","proceeding":"AKBC 2021 10","authors":["Matan Hasson","Jonathan Berant"],"abstract":"QDMR is a meaning representation for complex questions, which decomposes questions into a sequence of atomic steps. While state-of-the-art QDMR parsers use the common sequence-to-sequence (seq2seq) approach, a QDMR structure fundamentally describes labeled relations between spans in the input question, and thus dependency-based approaches seem appropriate for this task. In this work, we present a QDMR parser that is based on dependency graphs (DGs), where nodes in the graph are words and edges describe logical relations that correspond to the different computation steps. We propose (a) a non-autoregressive graph parser, where all graph edges are computed simultaneously, and (b) a seq2seq parser that uses gold graph as auxiliary supervision. We find that a graph parser leads to a moderate reduction in performance (0.47 to 0.44), but to a 16x speed-up in inference time due to the non-autoregressive nature of the parser, and to improved sample complexity compared to a seq2seq model. Second, a seq2seq model trained with auxiliary graph supervision has better generalization to new domains compared to a seq2seq model, and also performs better on questions with long sequences of computation steps.","url_abs":"https://arxiv.org/abs/2104.08647v1","url_pdf":"https://arxiv.org/pdf/2104.08647v1.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":"question-decomposition-with-dependency-graphs","repo_url":"https://github.com/matanhasson/qdecomp_with_dependency_graphs","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"seq2seq","method_name":"Seq2Seq"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2104.08647","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.08647"}},"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/matanhasson/qdecomp_with_dependency_graphs","reach":null}],"summary":{"ran_draft_wrong":1,"unverified":2},"by_repo_kind":{"official":{"samples":3,"ran":1,"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":3,"samples":[{"code_sha256_prefix":"b01af934729434d1","entry":"compare_performances","repo":"matanhasson/qdecomp_with_dependency_graphs","repo_kind":"official","path":"evaluation/normal_form/normalized_graph_matcher.py","file_url":"https://github.com/matanhasson/qdecomp_with_dependency_graphs/blob/HEAD/evaluation/normal_form/normalized_graph_matcher.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b01af934729434d1"}},{"code_sha256_prefix":"9ef92999cca12e69","entry":"best","repo":"matanhasson/qdecomp_with_dependency_graphs","repo_kind":"official","path":"scripts/train/run_experiments.py","file_url":"https://github.com/matanhasson/qdecomp_with_dependency_graphs/blob/HEAD/scripts/train/run_experiments.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9ef92999cca12e69"}},{"code_sha256_prefix":"646fd88886b2f30d","entry":"eval","repo":"matanhasson/qdecomp_with_dependency_graphs","repo_kind":"official","path":"scripts/train/run_experiments.py","file_url":"https://github.com/matanhasson/qdecomp_with_dependency_graphs/blob/HEAD/scripts/train/run_experiments.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"646fd88886b2f30d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}