Lune

EMNLP Findings2023

WordNet Is All You Need: A Surprisingly Effective Unsupervised Method for Graded Lexical Entailment

Joseph Renner, Pascal Denis, Rémi Gilleron

Abstract

We propose a simple unsupervised approach which exclusively relies on WordNet (Miller, 1995) for predicting graded lexical entailment (GLE) in English. Inspired by the seminal work of Resnik (1995), our method models GLE as the sum of two information-theoretic scores: a symmetric semantic similarity score and an asymmetric specificity loss score, both exploiting the hierarchical synset structure of Word-Net. Our approach also includes a simple disambiguation mechanism to handle polysemy in a given word pair. Despite its simplicity, our method achieves performance above the state of the art (Spearman ρ = 0.75) on HyperLex (Vulic et al., 2017), the largest GLE dataset, outperforming all previous methods, including specialized word embeddings approaches that use WordNet as weak supervision.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

Builds onCited byLeft to right by year; the more cited, the higher.

Builds on2

  1. Pythia: A Suite for Analyzing Large Language Models Across Training and ScalingStella Biderman, Hailey Schoelkopf, Quentin Gregory Anthony, Herbie Bradley et al.ICML 2023 · 1,822 citations
  2. DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding SharingPengcheng He, Jianfeng Gao, Weizhu ChenICLR 2023 · 394 citations

Related papers

  1. Lexical Entailment with Hierarchy Representations by Deep Metric LearningNaomi Sato, Masaru Isonuma, Kimitaka Asatani, Shoya Ishizuka et al.EMNLP Findings 2022 · 1 citation
  2. Breaking Through the 80% Glass Ceiling: Raising the State of the Art in Word Sense Disambiguation by Incorporating Knowledge Graph InformationMichele Bevilacqua, Roberto NavigliACL 2020 · 145 citations
  3. No clues good clues: out of context Lexical Relation ClassificationLucia Pitarch, Jordi Bernad, Lacramioara Dranca, Carlos Bobed Lisbona et al.ACL 2023 · 4 citations
  4. To Word Senses and Beyond: Inducing Concepts with Contextualized Language ModelsBastien Liétard, Pascal Denis, Mikaela KellerEMNLP 2024
  5. With More Contexts Comes Better Performance: Contextualized Sense Embeddings for All-Round Word Sense DisambiguationBianca Scarlini, Tommaso Pasini, Roberto NavigliEMNLP 2020 · 95 citations
Dusk over the sea between two cliffs drawn in fine vertical lines