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

by   Rohan Gupta, et al.

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.



There are no comments yet.


page 4


Parameter-Efficient Neural Reranking for Cross-Lingual and Multilingual Retrieval

State-of-the-art neural (re)rankers are notoriously data hungry which - ...

An Exploratory Analysis of Multilingual Word-Level Quality Estimation with Cross-Lingual Transformers

Most studies on word-level Quality Estimation (QE) of machine translatio...

XL-WiC: A Multilingual Benchmark for Evaluating Semantic Contextualization

The ability to correctly model distinct meanings of a word is crucial fo...

SML: a new Semantic Embedding Alignment Transformer for efficient cross-lingual Natural Language Inference

The ability of Transformers to perform with precision a variety of tasks...

PALI at SemEval-2021 Task 2: Fine-Tune XLM-RoBERTa for Word in Context Disambiguation

This paper presents the PALI team's winning system for SemEval-2021 Task...

Multilingual Counter Narrative Type Classification

The growing interest in employing counter narratives for hatred interven...

Zhestyatsky at SemEval-2021 Task 2: ReLU over Cosine Similarity for BERT Fine-tuning

This paper presents our contribution to SemEval-2021 Task 2: Multilingua...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.