Constructing A Corpus Of Figurative Language For a Tweet Classification and Retrieval Task.
FIRE '14: Proceedings of the 6th Annual Meeting of the Forum for Information Retrieval Evaluation(2014)
摘要
Twitter is an intriguing source of topical content for tasks involving the detection of phenomena such as sarcasm and metaphor. The hashtags that users employ to self-annotate their own micro-texts can often facilitate the targeted retrieval of texts with the desired characteristics. Though tweets tagged with #sarcasm are highly likely to be sarcastic, the lack of a topic model for sarcastic tweets makes it difficult to detect when such tags are used in the expected way, or indeed, to retrieve tweets that are not explicitly tagged in this way. In this study, we explore how a tweet-retrieval and classification system can benefit from a topic model when constructing a task-specific Twitter corpus, such as for irony, sarcasm or metaphor detection.
更多查看译文
关键词
figurative language,tweet classification,corpus,retrieval task
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要