{"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/combining-sentiment-lexica-with-a-multi-view","title":"Combining Sentiment Lexica with a Multi-View Variational Autoencoder","arxiv_id":"1904.02839","date":"2019-04-05","proceeding":"NAACL 2019 6","authors":["Alexander Hoyle","Lawrence Wolf-Sonkin","Hanna Wallach","Ryan Cotterell","Isabelle Augenstein"],"abstract":"When assigning quantitative labels to a dataset, different methodologies may\nrely on different scales. In particular, when assigning polarities to words in\na sentiment lexicon, annotators may use binary, categorical, or continuous\nlabels. Naturally, it is of interest to unify these labels from disparate\nscales to both achieve maximal coverage over words and to create a single, more\nrobust sentiment lexicon while retaining scale coherence. We introduce a\ngenerative model of sentiment lexica to combine disparate scales into a common\nlatent representation. We realize this model with a novel multi-view\nvariational autoencoder (VAE), called SentiVAE. We evaluate our approach via a\ndownstream text classification task involving nine English-Language sentiment\nanalysis datasets; our representation outperforms six individual sentiment\nlexica, as well as a straightforward combination thereof.","url_abs":"http://arxiv.org/abs/1904.02839v1","url_pdf":"http://arxiv.org/pdf/1904.02839v1.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":"combining-sentiment-lexica-with-a-multi-view","repo_url":"https://github.com/ahoho/SentiVAE","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"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":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}