Determining sentiment views of verbal multiword expressions using linguistic features

We examine the binary classification of sentiment views for verbal multiword expressions (MWEs). Sentiment views denote the perspective of the holder of some opinion. We distinguish between MWEs conveying the view of the speaker of the utterance (e.g., in The company reinvented the wheel the holder is the implicit speaker who criticizes the company for creating something already existing) and MWEs conveying the view of explicit entities participating in an opinion event (e.g., in Peter threw in the towel the holder is Peter having given up something). The task has so far been examined on unigram opinion words. Since many features found effective for unigrams are not usable for MWEs, we propose novel ones taking into account the internal structure of MWEs, a unigram sentiment-view lexicon and various information from Wiktionary. We also examine distributional methods and show that the corpus on which a representation is induced has a notable impact on the classification. We perform an extrinsic evaluation in the task of opinion holder extraction and show that the learnt knowledge also improves a state-of-the-art classifier trained on BERT. Sentiment-view classification is typically framed as a task in which only little labeled training data are available. As in the case of unigrams, we show that for MWEs a feature-based approach beats state-of-the-art generic methods.

Automated summary

This paper examines the binary classification of sentiment views for verbal multiword expressions (MWEs), distinguishing between MWEs conveying the view of the speaker and MWEs conveying the view of explicit entities. Novel features considering the internal structure of MWEs, a unigram sentiment-view lexicon, and information from Wiktionary are proposed. The study also shows the impact of the corpus used for representation induction on classification, and demonstrates the improvement of a state-of-the-art classifier trained on BERT using the learnt knowledge. Feature-based approach outperforms generic methods for MWEs, similar to unigrams.