LyS_ACoru\~na at SemEval-2022 Task 10: Repurposing Off-the-Shelf Tools for Sentiment Analysis as Semantic Dependency Parsing

TL;DR

This paper explores repurposing off-the-shelf tools like semantic dependency parsers and translation models for structured sentiment analysis across multiple languages, achieving competitive results in SemEval-2022 Task 10.

Contribution

It introduces a novel approach combining pre-trained language models, translation, and dependency parsing for multilingual sentiment analysis, with new datasets and methods for zero-shot and cross-lingual setups.

Findings

Achieved top-10 rankings in monolingual and cross-lingual setups

Demonstrated effectiveness of translation-based data augmentation

Found that merging all English treebanks improved results

Abstract

This paper addressed the problem of structured sentiment analysis using a bi-affine semantic dependency parser, large pre-trained language models, and publicly available translation models. For the monolingual setup, we considered: (i) training on a single treebank, and (ii) relaxing the setup by training on treebanks coming from different languages that can be adequately processed by cross-lingual language models. For the zero-shot setup and a given target treebank, we relied on: (i) a word-level translation of available treebanks in other languages to get noisy, unlikely-grammatical, but annotated data (we release as much of it as licenses allow), and (ii) merging those translated treebanks to obtain training data. In the post-evaluation phase, we also trained cross-lingual models that simply merged all the English treebanks and did not use word-level translations, and yet obtained better results. According to the official results, we ranked 8th and 9th in the monolingual and cross-lingual setups.