{"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/a-tree-based-decoder-for-neural-machine","title":"A Tree-based Decoder for Neural Machine Translation","arxiv_id":"1808.09374","date":"2018-08-28","proceeding":"EMNLP 2018 10","authors":["Xinyi Wang","Hieu Pham","Pengcheng Yin","Graham Neubig"],"abstract":"Recent advances in Neural Machine Translation (NMT) show that adding\nsyntactic information to NMT systems can improve the quality of their\ntranslations. Most existing work utilizes some specific types of\nlinguistically-inspired tree structures, like constituency and dependency parse\ntrees. This is often done via a standard RNN decoder that operates on a\nlinearized target tree structure. However, it is an open question of what\nspecific linguistic formalism, if any, is the best structural representation\nfor NMT. In this paper, we (1) propose an NMT model that can naturally generate\nthe topology of an arbitrary tree structure on the target side, and (2)\nexperiment with various target tree structures. Our experiments show the\nsurprising result that our model delivers the best improvements with balanced\nbinary trees constructed without any linguistic knowledge; this model\noutperforms standard seq2seq models by up to 2.1 BLEU points, and other methods\nfor incorporating target-side syntax by up to 0.7 BLEU.","url_abs":"http://arxiv.org/abs/1808.09374v1","url_pdf":"http://arxiv.org/pdf/1808.09374v1.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":"a-tree-based-decoder-for-neural-machine","repo_url":"https://github.com/cindyxinyiwang/TrDec_pytorch","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"nmt","task_name":"NMT"},{"task_slug":"open-question","task_name":"Open-Ended Question Answering"},{"task_slug":"translation","task_name":"Translation"}],"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":{"syntology_url":"https://syntology.ai/paper/1808.09374","atlas_url":"https://app.syntology.ai/?focus=1808.09374","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":"1808.09374"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1808.09374\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1808.09374"},"call":"get_concepts_for_paper(arxiv_id=\"1808.09374\")"}],"by_repo":[{"repo":"cindyxinyiwang/TrDec_pytorch","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":"260fa19ffbf4f48120c2b9f26126d690970df1650a7dff77d6a9c0585cbd3a32","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}