# Integrating Distributional Lexical Contrast into Word Embeddings for Antonym-Synonym Distinction

arXiv: https://arxiv.org/abs/1605.07766 · HTML: https://mlsanity.com/paper/1605.07766/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 May 2016.

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

- [Measuring and Improving Consistency in Pretrained Language Models](https://mlsanity.com/paper/2102.01017/) (2021)
- [Experience Report: Deep Learning-based System Log Analysis for Anomaly Detection](https://mlsanity.com/paper/2107.05908/) (2021)
- [LogGD:Detecting Anomalies from System Logs by Graph Neural Networks](https://mlsanity.com/paper/2209.07869/) (2022)
- [On the Effectiveness of Log Representation for Log-based Anomaly Detection](https://mlsanity.com/paper/2308.08736/) (2023)
- [A Survey On Neural Word Embeddings](https://mlsanity.com/paper/2110.01804/) (2021)
- [Memory-assisted prompt editing to improve GPT-3 after deployment](https://mlsanity.com/paper/2201.06009/) (2022)
- [Detecting LLM Hallucinations via Embedding Cluster Geometry: A Three-Type Taxonomy with Measurable Signatures](https://mlsanity.com/paper/2602.14259/) (2026)
- [Unsupervised Detection of Contextualized Embedding Bias with Application to Ideology](https://mlsanity.com/paper/2212.07547/) (2022)
- [Try with Simpler -- An Evaluation of Improved Principal Component Analysis in Log-based Anomaly Detection](https://mlsanity.com/paper/2308.12612/) (2023)
- [Antonym vs Synonym Distinction using InterlaCed Encoder NETworks (ICE-NET)](https://mlsanity.com/paper/2401.10045/) (2024)
- [Permutation invariant matrix statistics and computational language tasks](https://mlsanity.com/paper/2202.06829/) (2022)
- [TPLogAD: Unsupervised Log Anomaly Detection Based on Event Templates and Key Parameters](https://mlsanity.com/paper/2411.15250/) (2024)
- [A visual observation on the geometry of UMAP projections of the difference vectors of antonym and synonym word pair embeddings](https://mlsanity.com/paper/2603.24150/) (2026)

## Abstract (arXiv)

We propose a novel vector representation that integrates lexical contrast into distributional vectors and strengthens the most salient features for determining degrees of word similarity. The improved vectors significantly outperform standard models and distinguish antonyms from synonyms with an average precision of 0.66-0.76 across word classes (adjectives, nouns, verbs). Moreover, we integrate the lexical contrast vectors into the objective function of a skip-gram model. The novel embedding outperforms state-of-the-art models on predicting word similarities in SimLex-999, and on distinguishing antonyms from synonyms.