Think Globally, Embed Locally --- Locally Linear Meta-embedding of Words

TL;DR

This paper introduces an unsupervised locally linear meta-embedding method that combines pre-trained word embeddings by focusing on local neighborhoods, significantly improving performance across various NLP tasks.

Contribution

It proposes a novel locally linear approach for meta-embedding learning that outperforms previous global methods and unifies vector concatenation as a special case.

Findings

Meta-embeddings outperform previous methods on semantic tasks.

The method achieves state-of-the-art results in benchmark datasets.

Local neighborhood sensitivity improves embedding quality.

Abstract

Distributed word embeddings have shown superior performances in numerous Natural Language Processing (NLP) tasks. However, their performances vary significantly across different tasks, implying that the word embeddings learnt by those methods capture complementary aspects of lexical semantics. Therefore, we believe that it is important to combine the existing word embeddings to produce more accurate and complete \emph{meta-embeddings} of words. For this purpose, we propose an unsupervised locally linear meta-embedding learning method that takes pre-trained word embeddings as the input, and produces more accurate meta embeddings. Unlike previously proposed meta-embedding learning methods that learn a global projection over all words in a vocabulary, our proposed method is sensitive to the differences in local neighbourhoods of the individual source word embeddings. Moreover, we show that vector concatenation, a previously proposed highly competitive baseline approach for integrating word embeddings, can be derived as a special case of the proposed method. Experimental results on semantic similarity, word analogy, relation classification, and short-text classification tasks show that our meta-embeddings to significantly outperform prior methods in several benchmark datasets, establishing a new state of the art for meta-embeddings.