{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/second-order-unsupervised-neural-dependency","title":"Second-Order Unsupervised Neural Dependency Parsing","arxiv_id":"2010.14720","date":"2020-10-28","proceeding":"COLING 2020 8","authors":["Songlin Yang","Yong Jiang","Wenjuan Han","Kewei Tu"],"abstract":"Most of the unsupervised dependency parsers are based on first-order probabilistic generative models that only consider local parent-child information. Inspired by second-order supervised dependency parsing, we proposed a second-order extension of unsupervised neural dependency models that incorporate grandparent-child or sibling information. We also propose a novel design of the neural parameterization and optimization methods of the dependency models. In second-order models, the number of grammar rules grows cubically with the increase of vocabulary size, making it difficult to train lexicalized models that may contain thousands of words. To circumvent this problem while still benefiting from both second-order parsing and lexicalization, we use the agreement-based learning framework to jointly train a second-order unlexicalized model and a first-order lexicalized model. Experiments on multiple datasets show the effectiveness of our second-order models compared with recent state-of-the-art methods. Our joint model achieves a 10% improvement over the previous state-of-the-art parser on the full WSJ test set","url_abs":"https://arxiv.org/abs/2010.14720v1","url_pdf":"https://arxiv.org/pdf/2010.14720v1.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":"second-order-unsupervised-neural-dependency","repo_url":"https://github.com/sustcsonglin/second-order-neural-dmv","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"dependency-grammar-induction","task_name":"Dependency Grammar Induction"},{"task_slug":"dependency-parsing","task_name":"Dependency Parsing"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/dependency-grammar-induction-on-wsj","task":"Dependency Grammar Induction","dataset":"WSJ","model":"Joint training: sibling-NDMV + L-NDMV *","rank_in_archive_order":1,"of":1,"metrics":{"UAS":"67.5"},"uses_additional_data":false},{"leaderboard":"/sota/dependency-grammar-induction-on-wsj10","task":"Dependency Grammar Induction","dataset":"WSJ10","model":"Joint training: sibling-NDMV + L-NDMV *","rank_in_archive_order":1,"of":2,"metrics":{"UAS":"79.9"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2010.14720","atlas_url":"https://app.syntology.ai/?focus=2010.14720","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2010.14720"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2010.14720\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2010.14720"},"call":"get_concepts_for_paper(arxiv_id=\"2010.14720\")"}],"by_repo":[{"repo":"sustcsonglin/second-order-neural-dmv","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"eb568b3f15857a195e7006862bad3fd22a397be48ce0221f978e820ddc0c7ec6","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}