Paper: Identifying Event-Sentiment Association using Lexical Equivalence and Co-reference Approaches

ACL ID W11-0904
Title Identifying Event-Sentiment Association using Lexical Equivalence and Co-reference Approaches
Venue Proceedings of the ACL 2011 Workshop on Relational Models of Semantics
Session
Year 2011
Authors

In this paper, we have identified event and sen- timent expressions at word level from the sen- tences of TempEval-2010 corpus and evaluated their association in terms of lexical equivalence and co-reference. A hybrid approach that con- sists of Conditional Random Field (CRF) based machine learning framework in conjunction with several rule based strategies has been adopted for event identification within the TimeML framework. The strategies are based on semantic role labeling, WordNet relations and some handcrafted rules. The sentiment ex- pressions are identified simply based on the cues that are available in the sentiment lexicons such as Subjectivity Wordlist, SentiWordNet and WordNet Affect. The identification of lexi- cal equivalence between event and sentiment expressio...