Towards robust word embeddings for noisy texts
This addresses the challenge of handling noisy texts in social media for NLP applications, but it is incremental as it builds on existing skipgram models.
The paper tackled the problem of improving word embeddings for noisy texts like tweets by proposing a simple extension to the skipgram model using bridge-words, resulting in new embeddings that outperform baseline models on noisy texts across evaluation tasks while maintaining good performance on standard texts.
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.