# Word Sense Disambiguation using a Bidirectional LSTM

arXiv: https://arxiv.org/abs/1606.03568 · HTML: https://mlsanity.com/paper/1606.03568/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Jun 2016.

## Built on by (most cited first, 11 of 11)

- [Incorporating Word Sense Disambiguation in Neural Language Models](https://mlsanity.com/paper/2106.07967/) (2021)
- [Non-Parametric Few-Shot Learning for Word Sense Disambiguation](https://mlsanity.com/paper/2104.12677/) (2021)
- [Word Sense Disambiguation as a Game of Neurosymbolic Darts](https://mlsanity.com/paper/2307.16663/) (2023)
- [Detection of Non-recorded Word Senses in English and Swedish](https://mlsanity.com/paper/2403.02285/) (2024)
- [Training Bi-Encoders for Word Sense Disambiguation](https://mlsanity.com/paper/2105.10146/) (2021)
- [Meta-Learning with Variational Semantic Memory for Word Sense Disambiguation](https://mlsanity.com/paper/2106.02960/) (2021)
- [Context-gloss Augmentation for Improving Word Sense Disambiguation](https://mlsanity.com/paper/2110.07174/) (2021)
- [SANDWiCH: Semantical Analysis of Neighbours for Disambiguating Words in Context ad Hoc](https://mlsanity.com/paper/2503.05958/) (2025)
- [SensPick: Sense Picking for Word Sense Disambiguation](https://mlsanity.com/paper/2102.05260/) (2021)
- [PolyBERT: Fine-Tuned Poly Encoder BERT-Based Model for Word Sense Disambiguation](https://mlsanity.com/paper/2506.00968/) (2025)
- [Forecasting User Interests Through Topic Tag Predictions in Online Health Communities](https://mlsanity.com/paper/2211.02789/) (2022)

## Abstract (arXiv)

In this paper we present a clean, yet effective, model for word sense disambiguation. Our approach leverage a bidirectional long short-term memory network which is shared between all words. This enables the model to share statistical strength and to scale well with vocabulary size. The model is trained end-to-end, directly from the raw text to sense labels, and makes effective use of word order. We evaluate our approach on two standard datasets, using identical hyperparameter settings, which are in turn tuned on a third set of held out data. We employ no external resources (e.g. knowledge graphs, part-of-speech tagging, etc), language specific features, or hand crafted rules, but still achieve statistically equivalent results to the best state-of-the-art systems, that employ no such limitations.