{"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/efficient-second-order-treecrf-for-neural","title":"Efficient Second-Order TreeCRF for Neural Dependency Parsing","arxiv_id":"2005.00975","date":"2020-05-03","proceeding":"ACL 2020 6","authors":["Yu Zhang","Zhenghua Li","Min Zhang"],"abstract":"In the deep learning (DL) era, parsing models are extremely simplified with little hurt on performance, thanks to the remarkable capability of multi-layer BiLSTMs in context representation. As the most popular graph-based dependency parser due to its high efficiency and performance, the biaffine parser directly scores single dependencies under the arc-factorization assumption, and adopts a very simple local token-wise cross-entropy training loss. This paper for the first time presents a second-order TreeCRF extension to the biaffine parser. For a long time, the complexity and inefficiency of the inside-outside algorithm hinder the popularity of TreeCRF. To address this issue, we propose an effective way to batchify the inside and Viterbi algorithms for direct large matrix operation on GPUs, and to avoid the complex outside algorithm via efficient back-propagation. Experiments and analysis on 27 datasets from 13 languages clearly show that techniques developed before the DL era, such as structural learning (global TreeCRF loss) and high-order modeling are still useful, and can further boost parsing performance over the state-of-the-art biaffine parser, especially for partially annotated training data. We release our code at https://github.com/yzhangcs/crfpar.","url_abs":"https://arxiv.org/abs/2005.00975v2","url_pdf":"https://arxiv.org/pdf/2005.00975v2.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":"efficient-second-order-treecrf-for-neural","repo_url":"https://github.com/yzhangcs/crfpar","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"efficient-second-order-treecrf-for-neural","repo_url":"https://github.com/yzhangcs/parser","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"arc","task_name":"ARC"},{"task_slug":null,"task_name":"Chinese Dependency Parsing"},{"task_slug":"dependency-parsing","task_name":"Dependency Parsing"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/dependency-parsing-on-conll-2009","task":"Dependency Parsing","dataset":"CoNLL-2009","model":"CRFPar","rank_in_archive_order":1,"of":2,"metrics":{"LAS":"86.52","UAS":"89.63"},"uses_additional_data":false},{"leaderboard":"/sota/dependency-parsing-on-nlpcc-2019","task":"Dependency Parsing","dataset":"NLPCC-2019","model":"CRFPar","rank_in_archive_order":1,"of":1,"metrics":{"LAS":"72.33","UAS":"78.02"},"uses_additional_data":false},{"leaderboard":"/sota/dependency-parsing-on-penn-treebank","task":"Dependency Parsing","dataset":"Penn Treebank","model":"CRFPar","rank_in_archive_order":10,"of":22,"metrics":{"LAS":"94.49","UAS":"96.14"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2005.00975","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.00975"}},"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":"deterministic:regex_extraction","url":"https://github.com/yzhangcs/crfpar","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yzhangcs/parser","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_fixture":2,"unverified":1},"by_repo_kind":{"official":{"samples":3,"ran":2,"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":"d50ebb898113729e","entry":"inside","repo":"yzhangcs/crfpar","repo_kind":"official","path":"parser/utils/alg.py","file_url":"https://github.com/yzhangcs/crfpar/blob/HEAD/parser/utils/alg.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d50ebb898113729e"}},{"code_sha256_prefix":"91ae39cafd1dfd37","entry":"stripe","repo":"yzhangcs/crfpar","repo_kind":"official","path":"parser/utils/alg.py","file_url":"https://github.com/yzhangcs/crfpar/blob/HEAD/parser/utils/alg.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"91ae39cafd1dfd37"}},{"code_sha256_prefix":"6e68f8ea4fc8d230","entry":"crf","repo":"yzhangcs/crfpar","repo_kind":"official","path":"parser/utils/alg.py","file_url":"https://github.com/yzhangcs/crfpar/blob/HEAD/parser/utils/alg.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":"6e68f8ea4fc8d230"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}