{"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/emotion-representation-mapping-for-automatic","title":"Emotion Representation Mapping for Automatic Lexicon Construction (Mostly) Performs on Human Level","arxiv_id":"1806.08890","date":"2018-06-23","proceeding":"COLING 2018 8","authors":["Sven Buechel","Udo Hahn"],"abstract":"Emotion Representation Mapping (ERM) has the goal to convert existing emotion\nratings from one representation format into another one, e.g., mapping\nValence-Arousal-Dominance annotations for words or sentences into Ekman's Basic\nEmotions and vice versa. ERM can thus not only be considered as an alternative\nto Word Emotion Induction (WEI) techniques for automatic emotion lexicon\nconstruction but may also help mitigate problems that come from the\nproliferation of emotion representation formats in recent years. We propose a\nnew neural network approach to ERM that not only outperforms the previous\nstate-of-the-art. Equally important, we present a refined evaluation\nmethodology and gather strong evidence that our model yields results which are\n(almost) as reliable as human annotations, even in cross-lingual settings.\nBased on these results we generate new emotion ratings for 13 typologically\ndiverse languages and claim that they have near-gold quality, at least.","url_abs":"http://arxiv.org/abs/1806.08890v1","url_pdf":"http://arxiv.org/pdf/1806.08890v1.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":"emotion-representation-mapping-for-automatic","repo_url":"https://github.com/JULIELab/EmoMap","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1806.08890","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}