Semi-automatic WordNet Linking using Word Embeddings

TL;DR

This paper presents a semi-automatic method for linking WordNet synsets across languages using word embeddings, significantly aiding human experts in maintaining accurate multilingual lexical resources.

Contribution

It introduces a novel embedding-based approach that ranks candidate synsets for linking, achieving high accuracy in top-10 retrieval for WordNet synsets.

Findings

60% of synsets have correct link in top 10

70% accuracy for noun synsets

Reduces manual effort in WordNet linking

Abstract

Wordnets are rich lexico-semantic resources. Linked wordnets are extensions of wordnets, which link similar concepts in wordnets of different languages. Such resources are extremely useful in many Natural Language Processing (NLP) applications, primarily those based on knowledge-based approaches. In such approaches, these resources are considered as gold standard/oracle. Thus, it is crucial that these resources hold correct information. Thereby, they are created by human experts. However, manual maintenance of such resources is a tedious and costly affair. Thus techniques that can aid the experts are desirable. In this paper, we propose an approach to link wordnets. Given a synset of the source language, the approach returns a ranked list of potential candidate synsets in the target language from which the human expert can choose the correct one(s). Our technique is able to retrieve a winner synset in the top 10 ranked list for 60% of all synsets and 70% of noun synsets.