Conditional Generators of Words Definitions

2018/06/26 by Artyom Gadetsky, Gadetsky, Artyom, Ilya Yakubovskiy +3 · 2 citations
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Natural Language Processing Techniques #Text and Document Classification Technologies #Topic Modeling

paper · pdf · doi:10.48550/arxiv.1806.10090

openalex publication_date 2018/06/26 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

We explore recently introduced definition modeling technique that provided the tool for evaluation of different distributed vector representations of words through modeling dictionary definitions of words. In this work, we study the problem of word ambiguities in definition modeling and propose a possible solution by employing latent variable modeling and soft attention mechanisms. Our quantitative and qualitative evaluation and analysis of the model shows that taking into account words ambiguity and polysemy leads to performance improvement.

Citations

• Long Short-Term Memory
• Exploring the Limits of Language Modeling
• Pointer Sentinel Mixture Models
• Learning to Compute Word Embeddings On the Fly

Cited by

• Simplifications are Absolutists: How Simplified Language Reduces Word Sense Awareness in LLM-Generated Definitions
• Adapting Definition Modeling for New Languages: A Case Study on Belarusian

Related

• Definition Modeling: Learning to define word embeddings in natural\n language
• "Definition Modeling: To model definitions." Generating Definitions With Little to No Semantics
• VCDM: Leveraging Variational Bi-encoding and Deep Contextualized Word Representations for Improved Definition Modeling
• Exploiting Correlations Between Contexts and Definitions with Multiple Definition Modeling
• Overcoming Poor Word Embeddings with Word Definitions