An NLP Framework for Interpreting Implicit and Explicit Opinions in Text and Dialog (Academic Keynote Talk)

摘要

While previous sentiment analysis research has concentrated on the interpretation of explicitly stated opinions and attitudes, this work addresses the computational study of a type of opinion implicature (i.e., opinion-oriented inference) in text and dialog. This talk will describe a framework for representing and analyzing opinion implicatures which promises to contribute to deeper automatic interpretation of subjective language. In the course of understanding implicatures, the system recognizes implicit sentiments (and beliefs) toward various events and entities in the sentence, often attributed to different sources (holders) and of mixed polarities; thus, it produces a richer interpretation than is typical in opinion analysis.