UAlberta at SemEval-2021 Task 2: Determining Sense Synonymy via Translations

Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021), pages 763–770 Bangkok, Thailand (online), August 5–6, 2021. ©2021 Association for Computational Linguistics 763 UAlberta at SemEval-2021 Task 2: Determining Sense Synonymy via Translations Bradley Hauer, Hongchang Bao, Arnob Mallik, Grzegorz Kondrak Alberta Machine Intelligence Institute, Department of Computing Science University of Alberta, Edmonton, Canada {bmhauer,hongchan,amallik,gkondrak}@ualberta.ca Abstract We describe the University of Alberta systems for the SemEval-2021 Multilingual and Cross- lingual Word-in-Context (MCL-WiC) disam- biguation task. We explore the use of transla- tion information for deciding whether two dif- ferent tokens of the same word correspond to the same sense of the word. Our focus is on developing principled theoretical approaches which are grounded in linguistic phenomena, leading to more explainable models. We show that translations from multiple languages can be leveraged to improve the accuracy on the WiC task. 1 Introduction This paper describes the University of Alberta systems for SemEval-2021 Task 2: Multilingual and Cross-lingual Word-in-Context Disambigua- tion (Martelli et al., 2021). We focus on the monolingual (English) variant of the task, which is the same as the original WiC task (Pilehvar and Camacho-Collados, 2018). An instance of the WiC task consists of two sentences that share a focus word in common; the word may be inflected dif- ferently in each sentence (e.g. “they had searched his flat a few days before” and “the production of lithium from salt flats”) but will share the same lemma and part of speech. A WiC task system must decide, given such a pair of sentences, whether the focus tokens have the same meaning in both sen- tences. Systems are compared in terms of their accuracy, the percentage of test instances correctly identified as TRUE (same meaning) or FALSE (dif- ferent meaning). The dataset includes training, de- velopment, and testing splits; as our methods are unsupervised, we do not use the training data. The goal of this paper is an exploration of the use of translation information for the WiC task. The intuition underlying our work is that distinctions in meaning tend to be reflected in distinctions in translation. We have previously presented meth- ods leveraging translation information to improve word sense disambiguation (Luan et al., 2020), and most frequent sense detection (Hauer et al., 2019), and have demonstrated that word senses which share translations are, in general, seman- tically related (Hauer and Kondrak, 2020a). We have also presented theoretical formalizations of lexico-semantic phenomena which view synonymy and translation as two aspects of semantic equiva- lence (Hauer and Kondrak, 2020b). Our team ad- ditionally presented a method based on translation information (Hauer et al., 2020) for the SemEval- 2020 Task 2 on Predicting Multilingual and Cross- Lingual Lexical Entailment (Glavaˇs et al., 2020). In this task, we investigate whether translation can be used to detect semantic equivalence in context, just as in the aforementioned prior task we investigated whether translation can be used to detect lexical entailment between word types. Our focus is on de- veloping principled theoretical approaches which are grounded …

Content truncated to 500 words