# sense2vec - A Fast and Accurate Method for Word Sense Disambiguation In Neural Word Embeddings

arXiv: https://arxiv.org/abs/1511.06388 · HTML: https://mlsanity.com/paper/1511.06388/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Nov 2015.

## Built on by (most cited first, 20 of 20)

- [DialFact: A Benchmark for Fact-Checking in Dialogue](https://mlsanity.com/paper/2110.08222/) (2021)
- [Zero-shot Fact Verification by Claim Generation](https://mlsanity.com/paper/2105.14682/) (2021)
- [BiRdQA: A Bilingual Dataset for Question Answering on Tricky Riddles](https://mlsanity.com/paper/2109.11087/) (2021)
- [Leaf: Multiple-Choice Question Generation](https://mlsanity.com/paper/2201.09012/) (2022)
- [ArgRewrite V.2: an Annotated Argumentative Revisions Corpus](https://mlsanity.com/paper/2206.01677/) (2022)
- [Multi-sense embeddings through a word sense disambiguation process](https://mlsanity.com/paper/2101.08700/) (2021)
- [Deep Learning Approaches to Lexical Simplification: A Survey](https://mlsanity.com/paper/2305.12000/) (2023)
- [Pipeline and Dataset Generation for Automated Fact-checking in Almost Any Language](https://mlsanity.com/paper/2312.10171/) (2023)
- [Neural Sequence-to-Sequence Modeling with Attention by Leveraging Deep Learning Architectures for Enhanced Contextual Understanding in Abstractive Text Summarization](https://mlsanity.com/paper/2404.08685/) (2024)
- [Automated Testing and Improvement of Named Entity Recognition Systems](https://mlsanity.com/paper/2308.07937/) (2023)
- [Language Modelling Approaches to Adaptive Machine Translation](https://mlsanity.com/paper/2401.14559/) (2024)
- [PENTACET data -- 23 Million Contextual Code Comments and 250,000 SATD comments](https://mlsanity.com/paper/2303.14029/) (2023)
- [Hybrid-DMKG: A Hybrid Reasoning Framework over Dynamic Multimodal Knowledge Graphs for Multimodal Multihop QA with Knowledge Editing](https://mlsanity.com/paper/2512.00881/) (2025)
- [Network representation learning systematic review: ancestors and current development state](https://mlsanity.com/paper/2109.07583/) (2021)
- [A Comparative Study of Transformers on Word Sense Disambiguation](https://mlsanity.com/paper/2111.15417/) (2021)
- [Sense representations for Portuguese: experiments with sense embeddings and deep neural language models](https://mlsanity.com/paper/2109.00025/) (2021)
- [Adverse Media Mining for KYC and ESG Compliance](https://mlsanity.com/paper/2110.11542/) (2021)
- [Overlapping Word Removal is All You Need: Revisiting Data Imbalance in Hope Speech Detection](https://mlsanity.com/paper/2204.05488/) (2022)
- [Advancements in eHealth Data Analytics through Natural Language Processing and Deep Learning](https://mlsanity.com/paper/2401.10850/) (2024)
- [Tracing the Evolution of Word Embedding Techniques in Natural Language Processing](https://mlsanity.com/paper/2603.13271/) (2026)

## Abstract (arXiv)

Neural word representations have proven useful in Natural Language Processing (NLP) tasks due to their ability to efficiently model complex semantic and syntactic word relationships. However, most techniques model only one representation per word, despite the fact that a single word can have multiple meanings or "senses". Some techniques model words by using multiple vectors that are clustered based on context. However, recent neural approaches rarely focus on the application to a consuming NLP algorithm. Furthermore, the training process of recent word-sense models is expensive relative to single-sense embedding processes. This paper presents a novel approach which addresses these concerns by modeling multiple embeddings for each word based on supervised disambiguation, which provides a fast and accurate way for a consuming NLP model to select a sense-disambiguated embedding. We demonstrate that these embeddings can disambiguate both contrastive senses such as nominal and verbal senses as well as nuanced senses such as sarcasm. We further evaluate Part-of-Speech disambiguated embeddings on neural dependency parsing, yielding a greater than 8% average error reduction in unlabeled attachment scores across 6 languages.