{"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/deep-recurrent-models-with-fast-forward","title":"Deep Recurrent Models with Fast-Forward Connections for Neural Machine Translation","arxiv_id":"1606.04199","date":"2016-06-14","proceeding":"TACL 2016 1","authors":["Jie Zhou","Ying Cao","Xuguang Wang","Peng Li","Wei Xu"],"abstract":"Neural machine translation (NMT) aims at solving machine translation (MT)\nproblems using neural networks and has exhibited promising results in recent\nyears. However, most of the existing NMT models are shallow and there is still\na performance gap between a single NMT model and the best conventional MT\nsystem. In this work, we introduce a new type of linear connections, named\nfast-forward connections, based on deep Long Short-Term Memory (LSTM) networks,\nand an interleaved bi-directional architecture for stacking the LSTM layers.\nFast-forward connections play an essential role in propagating the gradients\nand building a deep topology of depth 16. On the WMT'14 English-to-French task,\nwe achieve BLEU=37.7 with a single attention model, which outperforms the\ncorresponding single shallow model by 6.2 BLEU points. This is the first time\nthat a single NMT model achieves state-of-the-art performance and outperforms\nthe best conventional model by 0.7 BLEU points. We can still achieve BLEU=36.3\neven without using an attention mechanism. After special handling of unknown\nwords and model ensembling, we obtain the best score reported to date on this\ntask with BLEU=40.4. Our models are also validated on the more difficult WMT'14\nEnglish-to-German task.","url_abs":"http://arxiv.org/abs/1606.04199v3","url_pdf":"http://arxiv.org/pdf/1606.04199v3.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":"deep-recurrent-models-with-fast-forward","repo_url":"https://github.com/fstahlberg/tensor2tensor-usr","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"nmt","task_name":"NMT"},{"task_slug":"translation","task_name":"Translation"}],"methods":[{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/machine-translation-on-wmt2014-english-french","task":"Machine Translation","dataset":"WMT2014 English-French","model":"Deep-Att + PosUnk","rank_in_archive_order":38,"of":57,"metrics":{"BLEU score":"39.2","Hardware Burden":"119G"},"uses_additional_data":false},{"leaderboard":"/sota/machine-translation-on-wmt2014-english-french","task":"Machine Translation","dataset":"WMT2014 English-French","model":"Deep-Att","rank_in_archive_order":45,"of":57,"metrics":{"BLEU score":"35.9"},"uses_additional_data":false},{"leaderboard":"/sota/machine-translation-on-wmt2014-english-german","task":"Machine Translation","dataset":"WMT2014 English-German","model":"Deep-Att","rank_in_archive_order":79,"of":91,"metrics":{"BLEU score":"20.7","Hardware Burden":"119G"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1606.04199","atlas_url":"https://app.syntology.ai/?focus=1606.04199","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":"1606.04199"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1606.04199\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1606.04199"},"call":"get_concepts_for_paper(arxiv_id=\"1606.04199\")"}],"by_repo":[{"repo":"fstahlberg/tensor2tensor-usr","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1809.00125"],"harvested_for_calls":[{"arxiv_id":"1809.00125","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1809.00125"},"call":"get_harvested_code_for_paper(arxiv_id=\"1809.00125\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","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":"3e4cf25e3c71796ea3f604d1fd64d4e253dd96f11b8a8c39435a4ea877a26140","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}