Word Emdeddings through Hellinger PCA
This work addresses the need for efficient word embeddings in NLP, though it is incremental as it builds on existing co-occurrence matrix approaches.
The authors tackled the problem of computationally expensive neural language models for word embeddings by proposing a simplified method using Hellinger PCA on word co-occurrence matrices, achieving similar or better performance on NER and movie review tasks.
Word embeddings resulting from neural language models have been shown to be successful for a large variety of NLP tasks. However, such architecture might be difficult to train and time-consuming. Instead, we propose to drastically simplify the word embeddings computation through a Hellinger PCA of the word co-occurence matrix. We compare those new word embeddings with some well-known embeddings on NER and movie review tasks and show that we can reach similar or even better performance. Although deep learning is not really necessary for generating good word embeddings, we show that it can provide an easy way to adapt embeddings to specific tasks.