{"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/morphological-and-language-agnostic-word","title":"Morphological and Language-Agnostic Word Segmentation for NMT","arxiv_id":"1806.05482","date":"2018-06-14","proceeding":null,"authors":["Dominik Macháček","Jonáš Vidra","Ondřej Bojar"],"abstract":"The state of the art of handling rich morphology in neural machine\ntranslation (NMT) is to break word forms into subword units, so that the\noverall vocabulary size of these units fits the practical limits given by the\nNMT model and GPU memory capacity. In this paper, we compare two common but\nlinguistically uninformed methods of subword construction (BPE and STE, the\nmethod implemented in Tensor2Tensor toolkit) and two linguistically-motivated\nmethods: Morfessor and one novel method, based on a derivational dictionary.\nOur experiments with German-to-Czech translation, both morphologically rich,\ndocument that so far, the non-motivated methods perform better. Furthermore, we\niden- tify a critical difference between BPE and STE and show a simple pre-\nprocessing step for BPE that considerably increases translation quality as\nevaluated by automatic measures.","url_abs":"http://arxiv.org/abs/1806.05482v1","url_pdf":"http://arxiv.org/pdf/1806.05482v1.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":"morphological-and-language-agnostic-word","repo_url":"https://github.com/Gldkslfmsd/t2t_second","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":null,"task_name":"GPU"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"nmt","task_name":"NMT"},{"task_slug":"translation","task_name":"Translation"}],"methods":[{"method_slug":"bpe","method_name":"BPE"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1806.05482","atlas_url":"https://app.syntology.ai/?focus=1806.05482","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":"1806.05482"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1806.05482\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1806.05482"},"call":"get_concepts_for_paper(arxiv_id=\"1806.05482\")"}],"by_repo":[{"repo":"Gldkslfmsd/t2t_second","kind":"listed","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":"dd6fe968109c385adfa2bf6a808965fb66f477a27ae26f9733c3c6e52b7da801","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}