{"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/learning-sentence-embeddings-using-recursive","title":"Learning sentence embeddings using Recursive Networks","arxiv_id":"1805.08353","date":"2018-05-22","proceeding":null,"authors":["Anson Bastos"],"abstract":"Learning sentence vectors that generalise well is a challenging task. In this\npaper we compare three methods of learning phrase embeddings: 1) Using LSTMs,\n2) using recursive nets, 3) A variant of the method 2 using the POS information\nof the phrase. We train our models on dictionary definitions of words to obtain\na reverse dictionary application similar to Felix et al. [1]. To see if our\nembeddings can be transferred to a new task we also train and test on the\nrotten tomatoes dataset [2]. We train keeping the sentence embeddings fixed as\nwell as with fine tuning.","url_abs":"http://arxiv.org/abs/1805.08353v1","url_pdf":"http://arxiv.org/pdf/1805.08353v1.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":"learning-sentence-embeddings-using-recursive","repo_url":"https://github.com/dyashkir/todo-ideas-links","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"pos","task_name":"POS"},{"task_slug":"reverse-dictionary","task_name":"Reverse Dictionary"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"sentence-embeddings","task_name":"Sentence Embeddings"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}