作者: Beata Beigman Klebanov , Jill Burstein , Nitin Madnani , Adam Faulkner , Joel Tetreault
DOI: 10.1007/978-3-642-28604-9_48
关键词: Process (engineering) 、 Paraphrase 、 Lexicon 、 Subjectivity 、 Sentiment analysis 、 Computer science 、 Natural language processing 、 Scratch 、 Artificial intelligence 、 Linguistics
摘要: While there are a number of subjectivity lexicons available for research purposes, none can be used commercially. We describe the process constructing lexicon(s) recognizing sentiment polarity in essays written by test-takers, to within commercial essay-scoring system. discuss ways expanding manually-built seed lexicon using dictionary-based, distributional in-domain and out-of-domain information, as well Amazon Mechanical Turk help "clean up" expansions. show feasibility family from scratch combination methods attain competitive performance with state-of-art research-only lexicons. Furthermore, this is first use, our knowledge, paraphrase generation system lexicon.