MCL@IITK at SemEval-2021 Task 2: Multilingual and Cross-lingual Word-in-Context Disambiguation using Augmented Data, Signals, and Transformers

TL;DR

This paper presents a transformer-based approach for multilingual and cross-lingual word-in-context disambiguation, leveraging data augmentation, signals, and ensemble methods to achieve top performance in SemEval-2021 Task 2.

Contribution

It introduces novel data augmentation techniques and signal enhancements for transformer models, improving multilingual and cross-lingual disambiguation performance.

Findings

Achieved first place in EN-EN and FR-FR sub-tasks.

Effective use of data augmentation with WiC, XL-WiC, and SemCor 3.0.

Zero-shot cross-lingual transfer with translate-test methods.

Abstract

In this work, we present our approach for solving the SemEval 2021 Task 2: Multilingual and Cross-lingual Word-in-Context Disambiguation (MCL-WiC). The task is a sentence pair classification problem where the goal is to detect whether a given word common to both the sentences evokes the same meaning. We submit systems for both the settings - Multilingual (the pair's sentences belong to the same language) and Cross-Lingual (the pair's sentences belong to different languages). The training data is provided only in English. Consequently, we employ cross-lingual transfer techniques. Our approach employs fine-tuning pre-trained transformer-based language models, like ELECTRA and ALBERT, for the English task and XLM-R for all other tasks. To improve these systems' performance, we propose adding a signal to the word to be disambiguated and augmenting our data by sentence pair reversal. We further augment the dataset provided to us with WiC, XL-WiC and SemCor 3.0. Using ensembles, we achieve strong performance in the Multilingual task, placing first in the EN-EN and FR-FR sub-tasks. For the Cross-Lingual setting, we employed translate-test methods and a zero-shot method, using our multilingual models, with the latter performing slightly better.