Predicting the semantic orientation of adjectives
ACL '98 Proceedings of the 35th Annual Meeting of the Association for Computational Linguistics and Eighth Conference of the European Chapter of the Association for Computational Linguistics
EMNLP '03 Proceedings of the 2003 conference on Empirical methods in natural language processing
Determining the sentiment of opinions
COLING '04 Proceedings of the 20th international conference on Computational Linguistics
Multi-perspective question answering using the OpQA corpus
HLT '05 Proceedings of the conference on Human Language Technology and Empirical Methods in Natural Language Processing
Comparative experiments on sentiment classification for online product reviews
AAAI'06 proceedings of the 21st national conference on Artificial intelligence - Volume 2
Opinion and generic question answering systems: a performance analysis
ACLShort '09 Proceedings of the ACL-IJCNLP 2009 Conference Short Papers
Convolution kernels for opinion holder extraction
HLT '10 Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics
Evaluating EmotiBlog robustness for sentiment analysis tasks
NLDB'11 Proceedings of the 16th international conference on Natural language processing and information systems
| Hi-index | 0.00 |
Nowadays, the Web contains large amounts of heterogeneous (factual and opinionated) data, which is becoming equally important for users to access. The need to efficiently manage this information leads to the necessity of building automatic systems that efficiently process it. In this paper, we propose and evaluate a series of techniques whose aim is to improve the performance of an Opinion Question Answering (OQA) system. We include additional resources and processes with the objective of limiting the sources of errors in the different stages involved-question analysis, answer retrieval and filtering, answer re-ranking. We propose new elements that are significant in these stages and show that their use improves the performance of the system. We conclude that the suggested techniques help to influences the task in a positive manner.