UU-Tax at SemEval-2022 Task 3: Improving the generalizability of language models for taxonomy classification through data augmentation

TL;DR

This paper introduces UU-Tax, a data augmentation and multi-task learning approach that enhances language models' ability to classify taxonomic relationships in sentences, achieving high accuracy in SemEval-2022 Task 3.

Contribution

It proposes a novel two-stage fine-tuning method with data augmentation for ELECTRA and a simple classifier using USE features, improving generalizability for taxonomy classification.

Findings

Achieved 91.25% F1 score in sub-task 1

Demonstrated improved robustness through data augmentation

Provided insights via error analysis

Abstract

This paper presents our strategy to address the SemEval-2022 Task 3 PreTENS: Presupposed Taxonomies Evaluating Neural Network Semantics. The goal of the task is to identify if a sentence is deemed acceptable or not, depending on the taxonomic relationship that holds between a noun pair contained in the sentence. For sub-task 1 -- binary classification -- we propose an effective way to enhance the robustness and the generalizability of language models for better classification on this downstream task. We design a two-stage fine-tuning procedure on the ELECTRA language model using data augmentation techniques. Rigorous experiments are carried out using multi-task learning and data-enriched fine-tuning. Experimental results demonstrate that our proposed model, UU-Tax, is indeed able to generalize well for our downstream task. For sub-task 2 -- regression -- we propose a simple classifier that trains on features obtained from Universal Sentence Encoder (USE). In addition to describing the submitted systems, we discuss other experiments that employ pre-trained language models and data augmentation techniques. For both sub-tasks, we perform error analysis to further understand the behaviour of the proposed models. We achieved a global F1_Binary score of 91.25% in sub-task 1 and a rho score of 0.221 in sub-task 2.