# Specialising Word Vectors for Lexical Entailment

arXiv: https://arxiv.org/abs/1710.06371 · HTML: https://mlsanity.com/paper/1710.06371/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Oct 2017.

## Built on by (most cited first, 18 of 18)

- [Compositional Entailment Learning for Hyperbolic Vision-Language Models](https://mlsanity.com/paper/2410.06912/) (2024)
- [Emergent Visual-Semantic Hierarchies in Image-Text Representations](https://mlsanity.com/paper/2407.08521/) (2024)
- [TaxoLLaMA: WordNet-based Model for Solving Multiple Lexical Semantic Tasks](https://mlsanity.com/paper/2403.09207/) (2024)
- [Low Anisotropy Sense Retrofitting (LASeR) : Towards Isotropic and Sense Enriched Representations](https://mlsanity.com/paper/2104.10833/) (2021)
- [Language Models for Lexical Inference in Context](https://mlsanity.com/paper/2102.05331/) (2021)
- [D2LLM: Decomposed and Distilled Large Language Models for Semantic Search](https://mlsanity.com/paper/2406.17262/) (2024)
- [PHyCLIP: ℓ1-Product of Hyperbolic Factors Unifies Hierarchy and Compositionality in Vision-Language Representation Learning](https://mlsanity.com/paper/2510.08919/) (2025)
- [CEMTM: Contextual Embedding-based Multimodal Topic Modeling](https://mlsanity.com/paper/2509.11465/) (2025)
- [RetroGAN: A Cyclic Post-Specialization System for Improving Out-of-Knowledge and Rare Word Representations](https://mlsanity.com/paper/2108.12941/) (2021)
- [Semantic Specialization for Knowledge-based Word Sense Disambiguation](https://mlsanity.com/paper/2304.11340/) (2023)
- [A Geometry-Aware Algorithm to Learn Hierarchical Embeddings in Hyperbolic Space](https://mlsanity.com/paper/2407.16641/) (2024)
- [HCCM: Hierarchical Cross-Granularity Contrastive and Matching Learning for Natural Language-Guided Drones](https://mlsanity.com/paper/2508.21539/) (2025)
- [Lexical semantics enhanced neural word embeddings](https://mlsanity.com/paper/2210.00754/) (2022)
- [Cross-Genre Argument Mining: Can Language Models Automatically Fill in Missing Discourse Markers?](https://mlsanity.com/paper/2306.04314/) (2023)
- [Order Embeddings from Merged Ontologies using Sketching](https://mlsanity.com/paper/2101.02158/) (2021)
- [Permutation invariant matrix statistics and computational language tasks](https://mlsanity.com/paper/2202.06829/) (2022)
- [An Evaluation Dataset for Legal Word Embedding: A Case Study On Chinese Codex](https://mlsanity.com/paper/2203.15173/) (2022)
- [Bhav-Net: Knowledge Transfer for Cross-Lingual Antonym vs Synonym Distinction via Dual-Space Graph Transformers](https://mlsanity.com/paper/2508.15792/) (2025)

## Abstract (arXiv)

We present LEAR (Lexical Entailment Attract-Repel), a novel post-processing method that transforms any input word vector space to emphasise the asymmetric relation of lexical entailment (LE), also known as the IS-A or hyponymy-hypernymy relation. By injecting external linguistic constraints (e.g., WordNet links) into the initial vector space, the LE specialisation procedure brings true hyponymy-hypernymy pairs closer together in the transformed Euclidean space. The proposed asymmetric distance measure adjusts the norms of word vectors to reflect the actual WordNet-style hierarchy of concepts. Simultaneously, a joint objective enforces semantic similarity using the symmetric cosine distance, yielding a vector space specialised for both lexical relations at once. LEAR specialisation achieves state-of-the-art performance in the tasks of hypernymy directionality, hypernymy detection, and graded lexical entailment, demonstrating the effectiveness and robustness of the proposed asymmetric specialisation model.