UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

How Well Can We Predict Hypernyms from Word Embeddings? A Dataset-Centric Analysis

Ivan Sanchez Carmona, V; Riedel, S; (2017) How Well Can We Predict Hypernyms from Word Embeddings? A Dataset-Centric Analysis. In: Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers. (pp. pp. 401-407). Association for Computational Linguistics: Valencia, Spain. Green open access

[thumbnail of E17-2064.pdf]
Preview
Text
E17-2064.pdf - Published Version

Download (183kB) | Preview

Abstract

One key property of word embeddings currently under study is their capacity to encode hypernymy. Previous works have used supervised models to recover hypernymy structures from embeddings. However, the overall results do not clearly show how well we can recover such structures. We conduct the first dataset-centric analysis that shows how only the Baroni dataset provides consistent results. We empirically show that a possible reason for its good performance is its alignment to dimensions specific of hypernymy: generality and similarity.

Type: Proceedings paper
Title: How Well Can We Predict Hypernyms from Word Embeddings? A Dataset-Centric Analysis
Event: 15th Conference of the European Chapter of the Association for Computational Linguistics
ISBN-13: 9781510838604
Open access status: An open access version is available from UCL Discovery
Publisher version: http://aclweb.org/anthology/E17-2064
Language: English
Additional information: This version is the version of record. For information on re-use, please refer to the publisher’s terms and conditions.
UCL classification: UCL
UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science
URI: https://discovery.ucl.ac.uk/id/eprint/10064232
Downloads since deposit
89Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item