Cookies
Usamos cookies para melhorar nosso site e a sua experiência. Ao continuar a navegar no site, você aceita a nossa política de cookies. Ver mais
Aceitar Rejeitar
  • Menu
Tópicos
de interesse
Detalhes

Detalhes

  • Nome

    Daniel Bouçanova Loureiro
  • Cluster

    Informática
  • Cargo

    Assistente de Investigação
  • Desde

    01 novembro 2017
003
Publicações

2019

Language Modelling Makes Sense: Propagating Representations through Word Net for Full-Coverage Word Sense Disambiguation

Autores
Loureiro, D; Jorge, AM;

Publicação
57TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2019)

Abstract
Contextual embeddings represent a new generation of semantic representations learned from Neural Language Modelling (NLM) that addresses the issue of meaning conflation hampering traditional word embeddings. In this work, we show that contextual embeddings can be used to achieve unprecedented gains in Word Sense Disambiguation (WSD) tasks. Our approach focuses on creating sense-level embeddings with full-coverage of WordNet, and without recourse to explicit knowledge of sense distributions or task-specific modelling. As a result, a simple Nearest Neighbors (k-NN) method using our representations is able to consistently surpass the performance of previous systems using powerful neural sequencing models. We also analyse the robustness of our approach when ignoring part-of-speech and lemma features, requiring disambiguation against the full sense inventory, and revealing shortcomings to be improved. Finally, we explore applications of our sense embeddings for concept-level analyses of contextual embeddings and their respective NLMs.

2018

Affordance Extraction and Inference based on Semantic Role Labeling

Autores
Loureiro, D; Jorge, A;

Publicação
CoRR

Abstract