{"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/a-systematic-study-of-leveraging-subword","title":"A Systematic Study of Leveraging Subword Information for Learning Word Representations","arxiv_id":"1904.07994","date":"2019-04-16","proceeding":"NAACL 2019 6","authors":["Yi Zhu","Ivan Vulić","Anna Korhonen"],"abstract":"The use of subword-level information (e.g., characters, character n-grams, morphemes) has become ubiquitous in modern word representation learning. Its importance is attested especially for morphologically rich languages which generate a large number of rare words. Despite a steadily increasing interest in such subword-informed word representations, their systematic comparative analysis across typologically diverse languages and different tasks is still missing. In this work, we deliver such a study focusing on the variation of two crucial components required for subword-level integration into word representation models: 1) segmentation of words into subword units, and 2) subword composition functions to obtain final word representations. We propose a general framework for learning subword-informed word representations that allows for easy experimentation with different segmentation and composition components, also including more advanced techniques based on position embeddings and self-attention. Using the unified framework, we run experiments over a large number of subword-informed word representation configurations (60 in total) on 3 tasks (general and rare word similarity, dependency parsing, fine-grained entity typing) for 5 languages representing 3 language types. Our main results clearly indicate that there is no \"one-sizefits-all\" configuration, as performance is both language- and task-dependent. We also show that configurations based on unsupervised segmentation (e.g., BPE, Morfessor) are sometimes comparable to or even outperform the ones based on supervised word segmentation.","url_abs":"https://arxiv.org/abs/1904.07994v2","url_pdf":"https://arxiv.org/pdf/1904.07994v2.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":"a-systematic-study-of-leveraging-subword","repo_url":"https://github.com/cambridgeltl/sw_study","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"dependency-parsing","task_name":"Dependency Parsing"},{"task_slug":"entity-typing","task_name":"Entity Typing"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"word-similarity","task_name":"Word Similarity"}],"methods":[{"method_slug":"bpe","method_name":"BPE"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1904.07994","atlas_url":"https://app.syntology.ai/?focus=1904.07994","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}