Exploring sentiment constructions: connecting deep learning models with linguistic construction
Part Of
Proceedings of the 35th Pacific Asia Conference on Language, Information and Computation, PACLIC 2021
Start Page
32
End Page
39
Date Issued
2021
Author(s)
Tseng, Yu-Hsiang
Abstract
This paper presents a linguistically motivated novel framework that automatically identifies sentiment constructions in a corpus with only sentiment-annotated sentences. Construction, a crucial concept developed in Construction Grammar, is a form-meaning pair that relates a pattern with a specific communicative function. However, handcrafting constructions is laborious and often leads to sparse coverage in practice. We address the problem with a construction induction framework which includes three components: a deep-learning-based predictive model to capture the sentiment aspects of the text, a dynamic word parser that agglomerate tokens into (multi-)words units, and a score assignment mechanism to weigh those units based on their contributions to predictions. Units that score highly in the last step are the candid sentiment constructions. They are automatically post-processed with their linguistic contexts to create the final constructions. We experiment with the proposed framework on a sentiment-annotated corpus of online consumer reviews from Taiwan telecom. The proposed framework correctly assigned higher importance to handcrafted constructions. Furthermore, new constructions identified by the framework are validated by annotators’ rating data. © 2021 Association for Computational Lingustics. All Rights Reserved.
Type
book part