{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/compositional-morphology-for-word","title":"Compositional Morphology for Word Representations and Language Modelling","arxiv_id":"1405.4273","date":"2014-05-16","proceeding":null,"authors":["Jan A. Botha","Phil Blunsom"],"abstract":"This paper presents a scalable method for integrating compositional\nmorphological representations into a vector-based probabilistic language model.\nOur approach is evaluated in the context of log-bilinear language models,\nrendered suitably efficient for implementation inside a machine translation\ndecoder by factoring the vocabulary. We perform both intrinsic and extrinsic\nevaluations, presenting results on a range of languages which demonstrate that\nour model learns morphological representations that both perform well on word\nsimilarity tasks and lead to substantial reductions in perplexity. When used\nfor translation into morphologically rich languages with large vocabularies,\nour models obtain improvements of up to 1.2 BLEU points relative to a baseline\nsystem using back-off n-gram models.","url_abs":"http://arxiv.org/abs/1405.4273v1","url_pdf":"http://arxiv.org/pdf/1405.4273v1.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":"compositional-morphology-for-word","repo_url":"https://github.com/yoonkim/lstm-char-cnn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"torch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"translation","task_name":"Translation"},{"task_slug":"word-similarity","task_name":"Word Similarity"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1405.4273","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}