{"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/deep-generative-model-for-joint-alignment-and","title":"Deep Generative Model for Joint Alignment and Word Representation","arxiv_id":"1802.05883","date":"2018-02-16","proceeding":"NAACL 2018 6","authors":["Miguel Rios","Wilker Aziz","Khalil Sima'an"],"abstract":"This work exploits translation data as a source of semantically relevant\nlearning signal for models of word representation. In particular, we exploit\nequivalence through translation as a form of distributed context and jointly\nlearn how to embed and align with a deep generative model. Our EmbedAlign model\nembeds words in their complete observed context and learns by marginalisation\nof latent lexical alignments. Besides, it embeds words as posterior probability\ndensities, rather than point estimates, which allows us to compare words in\ncontext using a measure of overlap between distributions (e.g. KL divergence).\nWe investigate our model's performance on a range of lexical semantics tasks\nachieving competitive results on several standard benchmarks including natural\nlanguage inference, paraphrasing, and text similarity.","url_abs":"http://arxiv.org/abs/1802.05883v3","url_pdf":"http://arxiv.org/pdf/1802.05883v3.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":"deep-generative-model-for-joint-alignment-and","repo_url":"https://github.com/uva-slpl/embedalign","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"natural-language-inference","task_name":"Natural Language Inference"},{"task_slug":"translation","task_name":"Translation"},{"task_slug":"text-similarity","task_name":"text similarity"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}