# Multi-sense Definition Modeling using Word Sense Decompositions

arXiv: https://arxiv.org/abs/1909.09483 · HTML: https://mlsanity.com/paper/1909.09483/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Sep 2019.

## Built on by (most cited first, 2 of 2)

- [IRB-NLP at SemEval-2022 Task 1: Exploring the Relationship Between Words and Their Semantic Representations](https://mlsanity.com/paper/2205.06840/) (2022)
- [WIKITIDE: A Wikipedia-Based Timestamped Definition Pairs Dataset](https://mlsanity.com/paper/2308.03582/) (2023)

## Abstract (arXiv)

Word embeddings capture syntactic and semantic information about words. Definition modeling aims to make the semantic content in each embedding explicit, by outputting a natural language definition based on the embedding. However, existing definition models are limited in their ability to generate accurate definitions for different senses of the same word. In this paper, we introduce a new method that enables definition modeling for multiple senses. We show how a Gumble-Softmax approach outperforms baselines at matching sense-specific embeddings to definitions during training. In experiments, our multi-sense definition model improves recall over a state-of-the-art single-sense definition model by a factor of three, without harming precision.