# Antonym-Synonym Classification Based on New Sub-space Embeddings

arXiv: https://arxiv.org/abs/1906.05612 · HTML: https://mlsanity.com/paper/1906.05612/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Jun 2019.

## Built on by (most cited first, 9 of 9)

- [MoRAL: MoE Augmented LoRA for LLMs' Lifelong Learning](https://mlsanity.com/paper/2402.11260/) (2024)
- [Prompt-SAW: Leveraging Relation-Aware Graphs for Textual Prompt Compression](https://mlsanity.com/paper/2404.00489/) (2024)
- [Dialectical Alignment: Resolving the Tension of 3H and Security Threats of LLMs](https://mlsanity.com/paper/2404.00486/) (2024)
- [GRI: Graph-based Relative Isomorphism of Word Embedding Spaces](https://mlsanity.com/paper/2310.12360/) (2023)
- [GARI: Graph Attention for Relative Isomorphism of Arabic Word Embeddings](https://mlsanity.com/paper/2310.13068/) (2023)
- [Antonym vs Synonym Distinction using InterlaCed Encoder NETworks (ICE-NET)](https://mlsanity.com/paper/2401.10045/) (2024)
- [#REVAL: a semantic evaluation framework for hashtag recommendation](https://mlsanity.com/paper/2305.18330/) (2023)
- [Bhav-Net: Knowledge Transfer for Cross-Lingual Antonym vs Synonym Distinction via Dual-Space Graph Transformers](https://mlsanity.com/paper/2508.15792/) (2025)
- [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)

Distinguishing antonyms from synonyms is a key challenge for many NLP applications focused on the lexical-semantic relation extraction. Existing solutions relying on large-scale corpora yield low performance because of huge contextual overlap of antonym and synonym pairs. We propose a novel approach entirely based on pre-trained embeddings. We hypothesize that the pre-trained embeddings comprehend a blend of lexical-semantic information and we may distill the task-specific information using Distiller, a model proposed in this paper. Later, a classifier is trained based on features constructed from the distilled sub-spaces along with some word level features to distinguish antonyms from synonyms. Experimental results show that the proposed model outperforms existing research on antonym synonym distinction in both speed and performance.