# VCDM: Leveraging Variational Bi-encoding and Deep Contextualized Word Representations for Improved Definition Modeling

arXiv: https://arxiv.org/abs/2010.03124 · HTML: https://mlsanity.com/paper/2010.03124/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Oct 2020.

## Built on by (most cited first, 13 of 13)

- [Multitasking Framework for Unsupervised Simple Definition Generation](https://mlsanity.com/paper/2203.12926/) (2022)
- [Understanding Jargon: Combining Extraction and Generation for Definition Modeling](https://mlsanity.com/paper/2111.07267/) (2021)
- [Assisting Language Learners: Automated Trans-Lingual Definition Generation via Contrastive Prompt Learning](https://mlsanity.com/paper/2306.06058/) (2023)
- [Fine-grained Contrastive Learning for Definition Generation](https://mlsanity.com/paper/2210.00543/) (2022)
- [Bird's Eye: Probing for Linguistic Graph Structures with a Simple Information-Theoretic Approach](https://mlsanity.com/paper/2105.02629/) (2021)
- [BLCU-ICALL at SemEval-2022 Task 1: Cross-Attention Multitasking Framework for Definition Modeling](https://mlsanity.com/paper/2204.07701/) (2022)
- [VER: Unifying Verbalizing Entities and Relations](https://mlsanity.com/paper/2211.11093/) (2022)
- [COMPILING: A Benchmark Dataset for Chinese Complexity Controllable Definition Generation](https://mlsanity.com/paper/2209.14614/) (2022)
- [Exploiting Correlations Between Contexts and Definitions with Multiple Definition Modeling](https://mlsanity.com/paper/2305.14717/) (2023)
- [Vec2Gloss: definition modeling leveraging contextualized vectors with Wordnet gloss](https://mlsanity.com/paper/2305.17855/) (2023)
- [3D-EX : A Unified Dataset of Definitions and Dictionary Examples](https://mlsanity.com/paper/2308.03043/) (2023)
- [Multilingual Definition Modeling](https://mlsanity.com/paper/2506.01489/) (2025)
- [LitMind Dictionary: An Open-Source Online Dictionary](https://mlsanity.com/paper/2204.11087/) (2022)

## Abstract (arXiv)

In this paper, we tackle the task of definition modeling, where the goal is to learn to generate definitions of words and phrases. Existing approaches for this task are discriminative, combining distributional and lexical semantics in an implicit rather than direct way. To tackle this issue we propose a generative model for the task, introducing a continuous latent variable to explicitly model the underlying relationship between a phrase used within a context and its definition. We rely on variational inference for estimation and leverage contextualized word embeddings for improved performance. Our approach is evaluated on four existing challenging benchmarks with the addition of two new datasets, "Cambridge" and the first non-English corpus "Robert", which we release to complement our empirical study. Our Variational Contextual Definition Modeler (VCDM) achieves state-of-the-art performance in terms of automatic and human evaluation metrics, demonstrating the effectiveness of our approach.