Product Feature Mining: Semantic Clues versus Syntactic Constituents

Product feature mining is a key subtask in fine-grained opinion mining. Previ-ous works often use syntax constituents in this task. However, syntax-based methods can only use discrete contextual informa-tion, which may suffer from data sparsity. This paper proposes a novel product fea-ture mining method which leverages lexi-cal and contextual semantic clues. Lexical semantic clue verifies whether a candidate term is related to the target product, and contextual semantic clue serves as a soft pattern miner to find candidates, which ex-ploits semantics of each word in context so as to alleviate the data sparsity prob-lem. We build a semantic similarity graph to encode lexical semantic clue, and em-ploy a convolutional neural model to cap-ture contextual semantic clue. Then Label Propagation is applied to combine both se-mantic clues. Experimental results show that our semantics-based method signif-icantly outperforms conventional syntax-based approaches, which not only mines product features more accurately, but also extracts more infrequent product features.