kpfriends at SemEval-2022 Task 2: NEAMER -- Named Entity Augmented Multi-word Expression Recognizer

TL;DR

The paper introduces NEAMER, a system leveraging transfer learning and locality features to improve multilingual idiomaticity detection, achieving state-of-the-art results and demonstrating enhanced training stability.

Contribution

It presents a novel approach combining non-compositionality knowledge transfer, cross-lingual fine-tuning, and locality features for idiom classification.

Findings

Achieved SOTA F1 score of 0.9395 in SemEval-2022 Task 2

Improved training stability over previous methods

Demonstrated effectiveness of non-compositionality transfer and locality features

Abstract

We present NEAMER -- Named Entity Augmented Multi-word Expression Recognizer. This system is inspired by non-compositionality characteristics shared between Named Entity and Idiomatic Expressions. We utilize transfer learning and locality features to enhance idiom classification task. This system is our submission for SemEval Task 2: Multilingual Idiomaticity Detection and Sentence Embedding Subtask A OneShot shared task. We achieve SOTA with F1 0.9395 during post-evaluation phase. We also observe improvement in training stability. Lastly, we experiment with non-compositionality knowledge transfer, cross-lingual fine-tuning and locality features, which we also introduce in this paper.