{"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/distilling-knowledge-for-search-based","title":"Distilling Knowledge for Search-based Structured Prediction","arxiv_id":"1805.11224","date":"2018-05-29","proceeding":"ACL 2018 7","authors":["Yijia Liu","Wanxiang Che","Huaipeng Zhao","Bing Qin","Ting Liu"],"abstract":"Many natural language processing tasks can be modeled into structured\nprediction and solved as a search problem. In this paper, we distill an\nensemble of multiple models trained with different initialization into a single\nmodel. In addition to learning to match the ensemble's probability output on\nthe reference states, we also use the ensemble to explore the search space and\nlearn from the encountered states in the exploration. Experimental results on\ntwo typical search-based structured prediction tasks -- transition-based\ndependency parsing and neural machine translation show that distillation can\neffectively improve the single model's performance and the final model achieves\nimprovements of 1.32 in LAS and 2.65 in BLEU score on these two tasks\nrespectively over strong baselines and it outperforms the greedy structured\nprediction models in previous literatures.","url_abs":"http://arxiv.org/abs/1805.11224v1","url_pdf":"http://arxiv.org/pdf/1805.11224v1.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":"distilling-knowledge-for-search-based","repo_url":"https://github.com/Oneplus/twpipe","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"dependency-parsing","task_name":"Dependency Parsing"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"prediction","task_name":"Prediction"},{"task_slug":"structured-prediction","task_name":"Structured Prediction"},{"task_slug":"transition-based-dependency-parsing","task_name":"Transition-Based Dependency Parsing"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1805.11224","atlas_url":"https://app.syntology.ai/?focus=1805.11224","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":"1805.11224"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1805.11224\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1805.11224"},"call":"get_concepts_for_paper(arxiv_id=\"1805.11224\")"}],"by_repo":[{"repo":"Oneplus/twpipe","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":"c7c577298e57fafcf52db61b51c0a3ad6ef9a1c14bab057ef20194ae4ce3ec4c","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}