Repository logo
 

Unseen word representation by aligning heterogeneous lexical semantic spaces

Accepted version
Peer-reviewed

Type

Article

Change log

Authors

Pilehvar, MT 
Kartsaklis, D 
Liò, P 

Abstract

Word embedding techniques heavily rely on the abundance of training data for individual words. Given the Zipfian distribution of words in natural language texts, a large number of words do not usually appear frequently or at all in the training data. In this paper we put forward a technique that exploits the knowledge encoded in lexical resources, such as WordNet, to induce embeddings for unseen words. Our approach adapts graph embedding and cross-lingual vector space transformation techniques in order to merge lexical knowledge encoded in ontologies with that derived from corpus statistics. We show that the approach can provide consistent performance improvements across multiple evaluation benchmarks: in-vitro, on multiple rare word similarity datasets, and in-vivo, in two downstream text classification tasks.

Description

Keywords

cs.CL, cs.CL, cs.AI, cs.LG

Journal Title

33rd AAAI Conference on Artificial Intelligence, AAAI 2019, 31st Innovative Applications of Artificial Intelligence Conference, IAAI 2019 and the 9th AAAI Symposium on Educational Advances in Artificial Intelligence, EAAI 2019

Conference Name

Journal ISSN

2159-5399
2374-3468

Volume Title

Publisher

Publisher DOI

Publisher URL

Rights

All rights reserved
Sponsorship
Engineering and Physical Sciences Research Council (EP/M005089/1)