ADBCMM : Acronym Disambiguation by Building Counterfactuals and Multilingual Mixing

TL;DR

This paper introduces ADBCMM, a novel method for acronym disambiguation that leverages counterfactuals and multilingual mixing to enhance performance in low-resource languages, achieving top results in French and Spanish.

Contribution

The paper presents a new acronym disambiguation approach that effectively improves low-resource language performance through data balancing and multilingual techniques.

Findings

Achieved first place in French and Spanish acronym disambiguation tasks.

Significantly improved low-resource language performance.

Demonstrated effectiveness of counterfactuals and multilingual mixing.

Abstract

Scientific documents often contain a large number of acronyms. Disambiguation of these acronyms will help researchers better understand the meaning of vocabulary in the documents. In the past, thanks to large amounts of data from English literature, acronym task was mainly applied in English literature. However, for other low-resource languages, this task is difficult to obtain good performance and receives less attention due to the lack of large amount of annotation data. To address the above issue, this paper proposes an new method for acronym disambiguation, named as ADBCMM, which can significantly improve the performance of low-resource languages by building counterfactuals and multilingual mixing. Specifically, by balancing data bias in low-resource langauge, ADBCMM will able to improve the test performance outside the data set. In SDU@AAAI-22 - Shared Task 2: Acronym Disambiguation, the proposed method won first place in French and Spanish. You can repeat our results here https://github.com/WENGSYX/ADBCMM.