Hierarchical Embeddings for Hypernymy Detection and Directionality

07/23/2017
by   Kim Anh Nguyen, et al.
0

We present a novel neural model HyperVec to learn hierarchical embeddings for hypernymy detection and directionality. While previous embeddings have shown limitations on prototypical hypernyms, HyperVec represents an unsupervised measure where embeddings are learned in a specific order and capture the hypernym-hyponym distributional hierarchy. Moreover, our model is able to generalize over unseen hypernymy pairs, when using only small sets of training data, and by mapping to other languages. Results on benchmark datasets show that HyperVec outperforms both state-of-the-art unsupervised measures and embedding models on hypernymy detection and directionality, and on predicting graded lexical entailment.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/18/2016

Relations such as Hypernymy: Identifying and Exploiting Hearst Patterns in Distributional Vectors for Lexical Entailment

We consider the task of predicting lexical entailment using distribution...
research
10/06/2017

Learning Word Embeddings for Hyponymy with Entailment-Based Distributional Semantics

Lexical entailment, such as hyponymy, is a fundamental issue in the sema...
research
04/05/2022

HyperBox: A Supervised Approach for Hypernym Discovery using Box Embeddings

Hypernymy plays a fundamental role in many AI tasks like taxonomy learni...
research
02/24/2020

Using Distributional Thesaurus Embedding for Co-hyponymy Detection

Discriminating lexical relations among distributionally similar words ha...
research
10/02/2017

Unsupervised Hypernym Detection by Distributional Inclusion Vector Embedding

Modeling hypernymy, such as poodle is-a dog, is an important generalizat...
research
04/26/2018

Hierarchical Density Order Embeddings

By representing words with probability densities rather than point vecto...
research
06/07/2019

On the Compositionality Prediction of Noun Phrases using Poincaré Embeddings

The compositionality degree of multiword expressions indicates to what e...

Please sign up or login with your details

Forgot password? Click here to reset