{"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/ntua-slp-at-semeval-2018-task-3-tracking","title":"NTUA-SLP at SemEval-2018 Task 3: Tracking Ironic Tweets using Ensembles of Word and Character Level Attentive RNNs","arxiv_id":"1804.06659","date":"2018-04-18","proceeding":"SEMEVAL 2018 6","authors":["Christos Baziotis","Nikos Athanasiou","Pinelopi Papalampidi","Athanasia Kolovou","Georgios Paraskevopoulos","Nikolaos Ellinas","Alexandros Potamianos"],"abstract":"In this paper we present two deep-learning systems that competed at\nSemEval-2018 Task 3 \"Irony detection in English tweets\". We design and ensemble\ntwo independent models, based on recurrent neural networks (Bi-LSTM), which\noperate at the word and character level, in order to capture both the semantic\nand syntactic information in tweets. Our models are augmented with a\nself-attention mechanism, in order to identify the most informative words. The\nembedding layer of our word-level model is initialized with word2vec word\nembeddings, pretrained on a collection of 550 million English tweets. We did\nnot utilize any handcrafted features, lexicons or external datasets as prior\ninformation and our models are trained end-to-end using back propagation on\nconstrained data. Furthermore, we provide visualizations of tweets with\nannotations for the salient tokens of the attention layer that can help to\ninterpret the inner workings of the proposed models. We ranked 2nd out of 42\nteams in Subtask A and 2nd out of 31 teams in Subtask B. However,\npost-task-completion enhancements of our models achieve state-of-the-art\nresults ranking 1st for both subtasks.","url_abs":"http://arxiv.org/abs/1804.06659v1","url_pdf":"http://arxiv.org/pdf/1804.06659v1.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":"ntua-slp-at-semeval-2018-task-3-tracking","repo_url":"https://github.com/FengJiaChunFromSYSU/ntua-slp-semeval2018","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"ntua-slp-at-semeval-2018-task-3-tracking","repo_url":"https://github.com/alexandra-chron/ntua-slp-semeval2018","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"ntua-slp-at-semeval-2018-task-3-tracking","repo_url":"https://github.com/cbaziotis/ntua-slp-semeval2018","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"word-embeddings","task_name":"Word Embeddings"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1804.06659","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}