Effective LSTMs for Target-Dependent Sentiment Classification
This work addresses the problem of accurately classifying sentiment towards specific targets in sentences for natural language processing applications, representing an incremental improvement over existing methods.
The paper tackled target-dependent sentiment classification by developing two target-dependent LSTM models that integrate target information, achieving state-of-the-art performance on a Twitter benchmark dataset without using syntactic parsers or external lexicons.
Target-dependent sentiment classification remains a challenge: modeling the semantic relatedness of a target with its context words in a sentence. Different context words have different influences on determining the sentiment polarity of a sentence towards the target. Therefore, it is desirable to integrate the connections between target word and context words when building a learning system. In this paper, we develop two target dependent long short-term memory (LSTM) models, where target information is automatically taken into account. We evaluate our methods on a benchmark dataset from Twitter. Empirical results show that modeling sentence representation with standard LSTM does not perform well. Incorporating target information into LSTM can significantly boost the classification accuracy. The target-dependent LSTM models achieve state-of-the-art performances without using syntactic parser or external sentiment lexicons.