JSALT 2015 -- Week 5 Plenary
Friday, Aug. 7:
- 10-11am Plenary seminar [EEB 105]
- 11:30am-1pm Team reports & lunch with speaker [EEB 303]
Context-aware Joint Inference for Fine-Grained Opinion Analysis
Existing approaches to fine-grained opinion extraction typically focus on extracting low-level information such as named entities and binary relations from individual sentences. These methods, however, are oblivious to the potentially useful information that can be obtained by considering the richer set of inter-connected relations expressed throughout the discourse. In this talk, I will discuss new methods for fine-grained opinion extraction that aim to rectify this. The methods are designed to jointly recognize multiple opinion-related entities and relations and to infer sentiment by leveraging lexical and discourse knowledge.
Claire Cardie is a Professor in the Computer Science and Information Science departments at Cornell University and was the founding Chair of Cornell's Information Science Department. She obtained her B.S. from Yale University and an M.S. and PhD at the University of Massachusetts at Amherst. Her research is in the area of Natural Language Processing and has focused most recently on the development of statistical learning methods for the automatic analysis of opinions, sentiment and deception in text --- for example, the identification of fake on-line reviews, disputes on social media sites and the argumentation structure of user comments. She has served elected terms as an executive committee member of the Association for the Advancement of Artificial Intelligence (AAAI), the Association for Computational Linguistics (ACL), its North American chapter (NAACL) and was Program Chair of the joint ACL/COLING conference in 2006. Cardie was also co-founder and chief scientist (2007-2015) of Appinions.com, a New York city-based startup.