{"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/translating-pro-drop-languages-with","title":"Translating Pro-Drop Languages with Reconstruction Models","arxiv_id":"1801.03257","date":"2018-01-10","proceeding":null,"authors":["Long-Yue Wang","Zhaopeng Tu","Shuming Shi","Tong Zhang","Yvette Graham","Qun Liu"],"abstract":"Pronouns are frequently omitted in pro-drop languages, such as Chinese,\ngenerally leading to significant challenges with respect to the production of\ncomplete translations. To date, very little attention has been paid to the\ndropped pronoun (DP) problem within neural machine translation (NMT). In this\nwork, we propose a novel reconstruction-based approach to alleviating DP\ntranslation problems for NMT models. Firstly, DPs within all source sentences\nare automatically annotated with parallel information extracted from the\nbilingual training corpus. Next, the annotated source sentence is reconstructed\nfrom hidden representations in the NMT model. With auxiliary training\nobjectives, in terms of reconstruction scores, the parameters associated with\nthe NMT model are guided to produce enhanced hidden representations that are\nencouraged as much as possible to embed annotated DP information. Experimental\nresults on both Chinese-English and Japanese-English dialogue translation tasks\nshow that the proposed approach significantly and consistently improves\ntranslation performance over a strong NMT baseline, which is directly built on\nthe training data annotated with DPs.","url_abs":"http://arxiv.org/abs/1801.03257v1","url_pdf":"http://arxiv.org/pdf/1801.03257v1.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":"translating-pro-drop-languages-with","repo_url":"https://github.com/longyuewangdcu/tvsub","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"nmt","task_name":"NMT"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1801.03257","atlas_url":"https://app.syntology.ai/?focus=1801.03257","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":"1801.03257"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1801.03257\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1801.03257"},"call":"get_concepts_for_paper(arxiv_id=\"1801.03257\")"}],"by_repo":[{"repo":"longyuewangdcu/tvsub","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":"e060fa2ecaeece59dcb519548a114d6b75985a8677d3f8372b64be17e315322e","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}