# Word Sense Disambiguation as a Game of Neurosymbolic Darts

arXiv: https://arxiv.org/abs/2307.16663 · HTML: https://mlsanity.com/paper/2307.16663/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 53 references that are in the map.
- First posted on arXiv 25 Jul 2023.

## Builds on (most cited first, 16 of 16)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Poincar'e Embeddings for Learning Hierarchical Representations](https://mlsanity.com/paper/1705.08039/) (2017)
- [Are Transformers universal approximators of sequence-to-sequence functions?](https://mlsanity.com/paper/1912.10077/) (2019)
- [A Survey of Transformers](https://mlsanity.com/paper/2106.04554/) (2021)
- [Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoning](https://mlsanity.com/paper/2205.09712/) (2022)
- [Neural-Symbolic Learning and Reasoning: A Survey and Interpretation](https://mlsanity.com/paper/1711.03902/) (2017)
- [Low-Dimensional Hyperbolic Knowledge Graph Embeddings](https://mlsanity.com/paper/2005.00545/) (2020)
- [Poincar'e GloVe: Hyperbolic Word Embeddings](https://mlsanity.com/paper/1810.06546/) (2018)
- [Probabilistic Embedding of Knowledge Graphs with Box Lattice Measures](https://mlsanity.com/paper/1805.06627/) (2018)
- [Language Modelling Makes Sense: Propagating Representations through WordNet for Full-Coverage Word Sense Disambiguation](https://mlsanity.com/paper/1906.10007/) (2019)
- [Improved Word Sense Disambiguation Using Pre-Trained Contextualized Word Representations](https://mlsanity.com/paper/1910.00194/) (2019)
- [Sense Vocabulary Compression through the Semantic Knowledge of WordNet for Neural Word Sense Disambiguation](https://mlsanity.com/paper/1905.05677/) (2019)
- [Adapting BERT for Word Sense Disambiguation with Gloss Selection Objective and Example Sentences](https://mlsanity.com/paper/2009.11795/) (2020)
- [Word Sense Disambiguation using a Bidirectional LSTM](https://mlsanity.com/paper/1606.03568/) (2016)
- [Word2Box: Capturing Set-Theoretic Semantics of Words using Box Embeddings](https://mlsanity.com/paper/2106.14361/) (2021)

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

- [A Survey on Lexical Ambiguity Detection and Word Sense Disambiguation](https://mlsanity.com/paper/2403.16129/) (2024)
- [Sphere Neural-Networks for Rational Reasoning](https://mlsanity.com/paper/2403.15297/) (2024)
- [SANDWiCH: Semantical Analysis of Neighbours for Disambiguating Words in Context ad Hoc](https://mlsanity.com/paper/2503.05958/) (2025)

## Abstract (arXiv)

Word Sense Disambiguation (WSD) is one of the hardest tasks in natural language understanding and knowledge engineering. The glass ceiling of 80% F1 score is recently achieved through supervised deep-learning, enriched by a variety of knowledge graphs. Here, we propose a novel neurosymbolic methodology that is able to push the F1 score above 90%. The core of our methodology is a neurosymbolic sense embedding, in terms of a configuration of nested balls in n-dimensional space. The centre point of a ball well-preserves word embedding, which partially fix the locations of balls. Inclusion relations among balls precisely encode symbolic hypernym relations among senses, and enable simple logic deduction among sense embeddings, which cannot be realised before. We trained a Transformer to learn the mapping from a contextualized word embedding to its sense ball embedding, just like playing the game of darts (a game of shooting darts into a dartboard). A series of experiments are conducted by utilizing pre-training n-ball embeddings, which have the coverage of around 70% training data and 75% testing data in the benchmark WSD corpus. The F1 scores in experiments range from 90.1% to 100.0% in all six groups of test data-sets (each group has 4 testing data with different sizes of n-ball embeddings). Our novel neurosymbolic methodology has the potential to break the ceiling of deep-learning approaches for WSD. Limitations and extensions of our current works are listed.