Siamese CBOW: Optimizing Word Embeddings for Sentence Representations
This work addresses a specific bottleneck in natural language processing for tasks requiring efficient sentence embeddings, though it is incremental as it builds on existing averaging methods.
The paper tackles the problem of suboptimal word embeddings for sentence representation by introducing Siamese CBOW, a neural network that trains word embeddings directly for averaging into sentence embeddings, and demonstrates its robustness by evaluating on 20 diverse datasets.
We present the Siamese Continuous Bag of Words (Siamese CBOW) model, a neural network for efficient estimation of high-quality sentence embeddings. Averaging the embeddings of words in a sentence has proven to be a surprisingly successful and efficient way of obtaining sentence embeddings. However, word embeddings trained with the methods currently available are not optimized for the task of sentence representation, and, thus, likely to be suboptimal. Siamese CBOW handles this problem by training word embeddings directly for the purpose of being averaged. The underlying neural network learns word embeddings by predicting, from a sentence representation, its surrounding sentences. We show the robustness of the Siamese CBOW model by evaluating it on 20 datasets stemming from a wide variety of sources.