Word Sense Disambiguation Based on Iterative Activation Spreading with Contextual Embeddings for Sense Matching

Użyj poniższego opisu do cytowania zasobu albo wyeksportuj go w wybranym formacie:
Janz, Arkadiusz and Piasecki, Maciej, 2023, Word Sense Disambiguation Based on Iterative Activation Spreading with Contextual Embeddings for Sense Matching, CLARIN-PL Repository, http://hdl.handle.net/11321/980.
Data
2023-01-01
Języki
Opis
Many knowledge-based solutions were proposed to solve Word Sense disambiguation (WSD) problem with limited annotated resources. Such WSD algorithms are able to cover very large sense repositories, but still being outperformed by supervised ones on benchmark data. In this paper, we start with analysis identifying key properties and issues in application of spreading activation algorithms in knowledge-based WSD, e.g. influence of the network local structures, interaction with context information and sense frequency. Taking our observations as a point of departure, we introduce a novel solution with new context-to-sense matching using BERT embeddings, iterative parallel spreading activation function and selective sense alignment using contextual BERT embeddings. The proposed solution obtains performance beyond the state-of-the-art for the contemporary knowledge-based WSD approaches for both English and Polish data.
Ten zasób jestCCi został udostępniony na licencji:Creative Commons - Attribution 4.0 International (CC BY 4.0)
Attribution Required

Dostęp do plików

Pliki w tym zasobie

Pobierz kompletny pakiet albo skopiuj gotowe polecenie do automatycznego pobierania.

Nazwa
Janz, Piasecki, WSD Based on Iterative Activation.pdf
Rozmiar
521.07 KB
Format
application/pdf
Opis
article
Suma kontrolna MD5
d52a4d99946765cd032f483ea5736fee
Preview
Podgląd pliku
  • Podgląd niedostępny

    Podgląd tego pliku nie został jeszcze wygenerowany. Spróbuj ponownie później albo skontaktuj się z administratorem systemu.