LANE: Lexical Adversarial Negative Examples for Word Sense Disambiguation

TL;DR

LANE introduces a novel adversarial training method that enhances neural language models' ability to distinguish subtle word meanings by generating challenging negative examples focused on target words, improving semantic discrimination.

Contribution

The paper presents LANE, a new adversarial training strategy that creates targeted negative examples to improve word sense disambiguation in neural models, addressing overfitting to global sentence features.

Findings

Improved performance on lexical semantic change detection.

Enhanced discrimination in word sense disambiguation tasks.

Qualitative analysis shows better capture of subtle meaning differences.

Abstract

Fine-grained word meaning resolution remains a critical challenge for neural language models (NLMs) as they often overfit to global sentence representations, failing to capture local semantic details. We propose a novel adversarial training strategy, called LANE, to address this limitation by deliberately shifting the model's learning focus to the target word. This method generates challenging negative training examples through the selective marking of alternate words in the training set. The goal is to force the model to create a greater separability between same sentences with different marked words. Experimental results on lexical semantic change detection and word sense disambiguation benchmarks demonstrate that our approach yields more discriminative word representations, improving performance over standard contrastive learning baselines. We further provide qualitative analyses showing that the proposed negatives lead to representations that better capture subtle meaning differences even in challenging environments. Our method is model-agnostic and can be integrated into existing representation learning frameworks.