A Cognitive Approach to Word Sense Disambiguation

Dutta, Sudakshina; Basu, Anupam

doi:10.1007/978-3-642-28604-9_18

Cited by 1 publication

(1 citation statement)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…When it comes to performing WSD, literature indicates several supervised techniques, where different types of classifiers can learn based on annotated datasets. A particularly interesting approach to address this task is the cognitive one, where the phenomenon of WSD is treated by modeling the cognitive process through ACT (Adaptive Control of Thought) [5] combined with RACE/A (Retrieval by Accumulating Evidence in an Architecture) [6], and such a modeling allows the outperforming of many systems for the task at hand [7].…”

Section: Introductionmentioning

confidence: 99%

Sparse associative memory based on contextual code learning for disambiguating word senses

Sobroza,

Marra,

Kim-Dufor

et al. 2019

Preprint

View full text Add to dashboard Cite

In recent literature, contextual pretrained Language Models (LMs) demonstrated their potential in generalizing the knowledge to several Natural Language Processing (NLP) tasks including supervised Word Sense Disambiguation (WSD), a challenging problem in the field of Natural Language Understanding (NLU). However, word representations from these models are still very dense, costly in terms of memory footprint, as well as minimally interpretable. In order to address such issues, we propose a new supervised biologically inspired technique for transferring large pre-trained language model representations into a compressed representation, for the case of WSD. Our produced representation contributes to increase the general interpretability of the framework and to decrease memory footprint, while enhancing performance.Preprint. Under review.

show abstract

Section: Introductionmentioning

confidence: 99%