LANE: Lexical Adversarial Negative Examples for Word Sense Disambiguation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917080193826816 |
|---|---|
| author | de Sá, Jader Martins Camboim Lee, Jooyoung Pruski, Cédric Da Silveira, Marcos |
| author_facet | de Sá, Jader Martins Camboim Lee, Jooyoung Pruski, Cédric Da Silveira, Marcos |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_11234 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LANE: Lexical Adversarial Negative Examples for Word Sense Disambiguation de Sá, Jader Martins Camboim Lee, Jooyoung Pruski, Cédric Da Silveira, Marcos Computation and Language 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. |
| title | LANE: Lexical Adversarial Negative Examples for Word Sense Disambiguation |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2511.11234 |