# Hypernyms under Siege: Linguistically-motivated Artillery for Hypernymy Detection

arXiv: https://arxiv.org/abs/1612.04460 · HTML: https://mlsanity.com/paper/1612.04460/

## Key facts

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

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

- [Norm of Word Embedding Encodes Information Gain](https://mlsanity.com/paper/2212.09663/) (2022)
- [MATCH: Metadata-Aware Text Classification in A Large Hierarchy](https://mlsanity.com/paper/2102.07349/) (2021)
- [Integrating Approaches to Word Representation](https://mlsanity.com/paper/2109.04876/) (2021)
- [Idioms, Probing and Dangerous Things: Towards Structural Probing for Idiomaticity in Vector Space](https://mlsanity.com/paper/2304.14333/) (2023)
- [More than just Frequency? Demasking Unsupervised Hypernymy Prediction Methods](https://mlsanity.com/paper/2106.00055/) (2021)
- [HyperBox: A Supervised Approach for Hypernym Discovery using Box Embeddings](https://mlsanity.com/paper/2204.02058/) (2022)
- [Multi-facet Universal Schema](https://mlsanity.com/paper/2103.15339/) (2021)
- [ASPER: Attention-based Approach to Extract Syntactic Patterns denoting Semantic Relations in Sentential Context](https://mlsanity.com/paper/2104.01523/) (2021)
- [Document Structure aware Relational Graph Convolutional Networks for Ontology Population](https://mlsanity.com/paper/2104.12950/) (2021)
- [Unsupervised Detection of Contextualized Embedding Bias with Application to Ideology](https://mlsanity.com/paper/2212.07547/) (2022)
- [Probing Taxonomic and Thematic Embeddings for Taxonomic Information](https://mlsanity.com/paper/2301.10656/) (2023)
- [Exploring Prompt-Based Methods for Zero-Shot Hypernym Prediction with Large Language Models](https://mlsanity.com/paper/2401.04515/) (2024)
- [Deep Learning and Natural Language Processing in the Field of Construction](https://mlsanity.com/paper/2501.07911/) (2025)

## Abstract (arXiv)

The fundamental role of hypernymy in NLP has motivated the development of many methods for the automatic identification of this relation, most of which rely on word distribution. We investigate an extensive number of such unsupervised measures, using several distributional semantic models that differ by context type and feature weighting. We analyze the performance of the different methods based on their linguistic motivation. Comparison to the state-of-the-art supervised methods shows that while supervised methods generally outperform the unsupervised ones, the former are sensitive to the distribution of training instances, hurting their reliability. Being based on general linguistic hypotheses and independent from training data, unsupervised measures are more robust, and therefore are still useful artillery for hypernymy detection.