Zhou, Yi and Bollegala, Danushka 
ORCID: 0000-0003-4476-7003
(2022)
On the Curious Case of l2 norm of Sense Embeddings.
In: Findings of the Association for Computational Linguistics: EMNLP 2022, 2022-12 - 2022-12, Abu Dabi.
|
Text
L2_norm_and_frequency_of_sense_embeddings__camera_ready_version_.pdf - Author Accepted Manuscript Download (1MB) | Preview |
Abstract
We show that the ℓ2 norm of a static sense embedding encodes information related to the frequency of that sense in the training corpus used to learn the sense embeddings. This finding can be seen as an extension of a previously known relationship for word embeddings to sense embeddings. Our experimental results show that, in spite of its simplicity, the ℓ2 norm of sense embeddings is a surprisingly effective feature for several word sense related tasks such as (a) most frequent sense prediction, (b) Word-in-Context (WiC), and (c) Word Sense Disambiguation (WSD). In particular, by simply including the ℓ2 norm of a sense embedding as a feature in a classifier, we show that we can improve WiC and WSD methods that use static sense embeddings.
| Item Type: | Conference or Workshop Item (Unspecified) |
|---|---|
| Depositing User: | Symplectic Admin |
| Date Deposited: | 12 Oct 2022 08:15 |
| Last Modified: | 15 Mar 2024 02:25 |
| DOI: | 10.18653/v1/2022.findings-emnlp.190 |
| Related URLs: | |
| URI: | https://livrepository.liverpool.ac.uk/id/eprint/3165407 |
Dimensions
Dimensions
