{"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/nelec-at-semeval-2019-task-3-think-twice","title":"NELEC at SemEval-2019 Task 3: Think Twice Before Going Deep","arxiv_id":"1904.03223","date":"2019-04-05","proceeding":"SEMEVAL 2019 6","authors":["Parag Agrawal","Anshuman Suri"],"abstract":"Existing Machine Learning techniques yield close to human performance on\ntext-based classification tasks. However, the presence of multi-modal noise in\nchat data such as emoticons, slang, spelling mistakes, code-mixed data, etc.\nmakes existing deep-learning solutions perform poorly. The inability of\ndeep-learning systems to robustly capture these covariates puts a cap on their\nperformance. We propose NELEC: Neural and Lexical Combiner, a system which\nelegantly combines textual and deep-learning based methods for sentiment\nclassification. We evaluate our system as part of the third task of 'Contextual\nEmotion Detection in Text' as part of SemEval-2019. Our system performs\nsignificantly better than the baseline, as well as our deep-learning model\nbenchmarks. It achieved a micro-averaged F1 score of 0.7765, ranking 3rd on the\ntest-set leader-board. Our code is available at\nhttps://github.com/iamgroot42/nelec","url_abs":"http://arxiv.org/abs/1904.03223v1","url_pdf":"http://arxiv.org/pdf/1904.03223v1.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":"nelec-at-semeval-2019-task-3-think-twice","repo_url":"https://github.com/iamgroot42/nelec","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"deep-learning","task_name":"Deep Learning"},{"task_slug":"emotion-recognition-in-conversation","task_name":"Emotion Recognition in Conversation"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"sentiment-classification","task_name":"Sentiment Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/emotion-recognition-in-conversation-on-ec","task":"Emotion Recognition in Conversation","dataset":"EC","model":"NELEC","rank_in_archive_order":1,"of":9,"metrics":{"Micro-F1":"0.7765"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}