{"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/joint-embedding-of-words-and-labels-for-text","title":"Joint Embedding of Words and Labels for Text Classification","arxiv_id":"1805.04174","date":"2018-05-10","proceeding":"ACL 2018 7","authors":["Guoyin Wang","Chunyuan Li","Wenlin Wang","Yizhe Zhang","Dinghan Shen","Xinyuan Zhang","Ricardo Henao","Lawrence Carin"],"abstract":"Word embeddings are effective intermediate representations for capturing\nsemantic regularities between words, when learning the representations of text\nsequences. We propose to view text classification as a label-word joint\nembedding problem: each label is embedded in the same space with the word\nvectors. We introduce an attention framework that measures the compatibility of\nembeddings between text sequences and labels. The attention is learned on a\ntraining set of labeled samples to ensure that, given a text sequence, the\nrelevant words are weighted higher than the irrelevant ones. Our method\nmaintains the interpretability of word embeddings, and enjoys a built-in\nability to leverage alternative sources of information, in addition to input\ntext sequences. Extensive results on the several large text datasets show that\nthe proposed framework outperforms the state-of-the-art methods by a large\nmargin, in terms of both accuracy and speed.","url_abs":"http://arxiv.org/abs/1805.04174v1","url_pdf":"http://arxiv.org/pdf/1805.04174v1.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":"joint-embedding-of-words-and-labels-for-text","repo_url":"https://github.com/guoyinwang/LEAM","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"joint-embedding-of-words-and-labels-for-text","repo_url":"https://github.com/ShuanDeMorian/Project_AT_News_Classification","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"sentiment-analysis","task_name":"Sentiment Analysis"},{"task_slug":"text-classification","task_name":"Text Classification"},{"task_slug":"text-classification-1","task_name":"text-classification"}],"methods":[{"method_slug":"interpretability","method_name":"Interpretability"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/sentiment-analysis-on-yelp-binary","task":"Sentiment Analysis","dataset":"Yelp Binary classification","model":"LEAM","rank_in_archive_order":18,"of":20,"metrics":{"Error":"4.69"},"uses_additional_data":false},{"leaderboard":"/sota/sentiment-analysis-on-yelp-fine-grained","task":"Sentiment Analysis","dataset":"Yelp Fine-grained classification","model":"LEAM","rank_in_archive_order":13,"of":17,"metrics":{"Error":"35.91"},"uses_additional_data":false},{"leaderboard":"/sota/text-classification-on-ag-news","task":"Text Classification","dataset":"AG News","model":"LEAM","rank_in_archive_order":14,"of":24,"metrics":{"Error":"7.55"},"uses_additional_data":false},{"leaderboard":"/sota/text-classification-on-dbpedia","task":"Text Classification","dataset":"DBpedia","model":"LEAM","rank_in_archive_order":11,"of":21,"metrics":{"Error":"0.98"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1805.04174","atlas_url":"https://app.syntology.ai/?focus=1805.04174","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}