{"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/patterns-versus-characters-in-subword-aware","title":"Patterns versus Characters in Subword-aware Neural Language Modeling","arxiv_id":"1709.00541","date":"2017-09-02","proceeding":null,"authors":["Rustem Takhanov","Zhenisbek Assylbekov"],"abstract":"Words in some natural languages can have a composite structure. Elements of\nthis structure include the root (that could also be composite), prefixes and\nsuffixes with which various nuances and relations to other words can be\nexpressed. Thus, in order to build a proper word representation one must take\ninto account its internal structure. From a corpus of texts we extract a set of\nfrequent subwords and from the latter set we select patterns, i.e. subwords\nwhich encapsulate information on character $n$-gram regularities. The selection\nis made using the pattern-based Conditional Random Field model with $l_1$\nregularization. Further, for every word we construct a new sequence over an\nalphabet of patterns. The new alphabet's symbols confine a local statistical\ncontext stronger than the characters, therefore they allow better\nrepresentations in ${\\mathbb{R}}^n$ and are better building blocks for word\nrepresentation. In the task of subword-aware language modeling, pattern-based\nmodels outperform character-based analogues by 2-20 perplexity points. Also, a\nrecurrent neural network in which a word is represented as a sum of embeddings\nof its patterns is on par with a competitive and significantly more\nsophisticated character-based convolutional architecture.","url_abs":"http://arxiv.org/abs/1709.00541v1","url_pdf":"http://arxiv.org/pdf/1709.00541v1.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":"patterns-versus-characters-in-subword-aware","repo_url":"https://github.com/zh3nis/pat-sum","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"arxiv_id_not_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"by_repo":[{"repo":"zh3nis/pat-sum","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":"67d1e47db929950dd0719be0f425be838b73af5fc2c00753b763f731028b845f","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}