# Using Multi-Sense Vector Embeddings for Reverse Dictionaries

arXiv: https://arxiv.org/abs/1904.01451 · HTML: https://mlsanity.com/paper/1904.01451/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Apr 2019.

## Built on by (most cited first, 3 of 3)

- [Towards Multi-Sense Cross-Lingual Alignment of Contextual Embeddings](https://mlsanity.com/paper/2103.06459/) (2021)
- [PREDICT: Persian Reverse Dictionary](https://mlsanity.com/paper/2105.00309/) (2021)
- [Advancing Arabic Reverse Dictionary Systems: A Transformer-Based Approach with Dataset Construction Guidelines](https://mlsanity.com/paper/2504.21475/) (2025)

## Abstract (arXiv)

Popular word embedding methods such as word2vec and GloVe assign a single vector representation to each word, even if a word has multiple distinct meanings. Multi-sense embeddings instead provide different vectors for each sense of a word. However, they typically cannot serve as a drop-in replacement for conventional single-sense embeddings, because the correct sense vector needs to be selected for each word. In this work, we study the effect of multi-sense embeddings on the task of reverse dictionaries. We propose a technique to easily integrate them into an existing neural network architecture using an attention mechanism. Our experiments demonstrate that large improvements can be obtained when employing multi-sense embeddings both in the input sequence as well as for the target representation. An analysis of the sense distributions and of the learned attention is provided as well.