Towards robust word embeddings for noisy texts

TL;DR

This paper introduces a novel extension to the skipgram model that uses bridge-words to improve word embeddings' robustness to noisy social media texts, outperforming baselines on various tasks.

Contribution

The paper proposes a simple yet effective method of adding bridge-words to enhance embeddings for noisy texts, a first in explicitly addressing this challenge beyond out-of-vocabulary support.

Findings

Embeddings with bridge-words outperform baselines on noisy social media texts.

The approach maintains good performance on standard texts.

The method improves both intrinsic and extrinsic evaluation results.

Abstract

Research on word embeddings has mainly focused on improving their performance on standard corpora, disregarding the difficulties posed by noisy texts in the form of tweets and other types of non-standard writing from social media. In this work, we propose a simple extension to the skipgram model in which we introduce the concept of bridge-words, which are artificial words added to the model to strengthen the similarity between standard words and their noisy variants. Our new embeddings outperform baseline models on noisy texts on a wide range of evaluation tasks, both intrinsic and extrinsic, while retaining a good performance on standard texts. To the best of our knowledge, this is the first explicit approach at dealing with this type of noisy texts at the word embedding level that goes beyond the support for out-of-vocabulary words.