ETMS@IITKGP at SemEval-2022 Task 10: Structured Sentiment Analysis Using A Generative Approach

TL;DR

This paper introduces a novel generative approach using a BART-based model for structured sentiment analysis, effectively extracting opinion tuples from text in both monolingual and cross-lingual settings.

Contribution

It presents a unified generative method for SSA, leveraging a modified BART architecture to generate opinion tuples, outperforming prior graph-based and sequence labeling approaches.

Findings

Achieved competitive Sentiment F1 scores on SemEval-2022 leaderboard.

Effective in both monolingual and cross-lingual subtasks.

Demonstrated the viability of generative models for structured sentiment extraction.

Abstract

Structured Sentiment Analysis (SSA) deals with extracting opinion tuples in a text, where each tuple (h, e, t, p) consists of h, the holder, who expresses a sentiment polarity p towards a target t through a sentiment expression e. While prior works explore graph-based or sequence labeling-based approaches for the task, we in this paper present a novel unified generative method to solve SSA, a SemEval2022 shared task. We leverage a BART-based encoder-decoder architecture and suitably modify it to generate, given a sentence, a sequence of opinion tuples. Each generated tuple consists of seven integers respectively representing the indices corresponding to the start and end positions of the holder, target, and expression spans, followed by the sentiment polarity class associated between the target and the sentiment expression. We perform rigorous experiments for both Monolingual and Cross-lingual subtasks, and achieve competitive Sentiment F1 scores on the leaderboard in both settings.