{"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/what-do-neural-machine-translation-models","title":"What do Neural Machine Translation Models Learn about Morphology?","arxiv_id":"1704.03471","date":"2017-04-11","proceeding":"ACL 2017 7","authors":["Yonatan Belinkov","Nadir Durrani","Fahim Dalvi","Hassan Sajjad","James Glass"],"abstract":"Neural machine translation (MT) models obtain state-of-the-art performance\nwhile maintaining a simple, end-to-end architecture. However, little is known\nabout what these models learn about source and target languages during the\ntraining process. In this work, we analyze the representations learned by\nneural MT models at various levels of granularity and empirically evaluate the\nquality of the representations for learning morphology through extrinsic\npart-of-speech and morphological tagging tasks. We conduct a thorough\ninvestigation along several parameters: word-based vs. character-based\nrepresentations, depth of the encoding layer, the identity of the target\nlanguage, and encoder vs. decoder representations. Our data-driven,\nquantitative evaluation sheds light on important aspects in the neural MT\nsystem and its ability to capture word structure.","url_abs":"http://arxiv.org/abs/1704.03471v3","url_pdf":"http://arxiv.org/pdf/1704.03471v3.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":"what-do-neural-machine-translation-models","repo_url":"https://github.com/boknilev/nmt-repr-analysis","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"morphological-tagging","task_name":"Morphological Tagging"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1704.03471","atlas_url":"https://app.syntology.ai/?focus=1704.03471","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":"1704.03471"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1704.03471\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1704.03471"},"call":"get_concepts_for_paper(arxiv_id=\"1704.03471\")"}],"by_repo":[{"repo":"boknilev/nmt-repr-analysis","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":"1feeaf0ea43d32b600ae0c7a616d7ee2bcc0a883257895363ca7bbf859b66117","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}