Papers with Word Sense Disambiguation
Ambiguity Meets Uncertainty: Investigating Uncertainty Estimation for Word Sense Disambiguation (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing supervised methods treat word sense disambiguation as a classification task but ignore uncertainty estimation (UE) in the real-world setting, the data is always noisy and out of distribution. |
| Approach: | They propose to use word sense disambiguation to determine an appropriate sense for a word given its context to determine the most appropriate sense. |
| Outcome: | The proposed model reflects data uncertainty satisfactorily but underestimates model uncertainty. |
Integrating Personalized PageRank into Neural Word Sense Disambiguation (2021.emnlp-main)
Copied to clipboard
| Challenge: | Neural Word Sense Disambiguation (WSD) uses pre-existing knowledge, but only close neighbors influence prediction. |
| Approach: | They propose to exploit WordNet graphs to improve a classification model by recomputing logits . they incorporate an online neural approximated PageRank to refine edge weights . |
| Outcome: | The proposed method improves the current state of the art in the field of Neural Word Sense Disambiguation (WSD) the proposed method exploits the global graph structure while keeping space requirements linear in the number of edges. |