CLMar 27, 2018
Mittens: An Extension of GloVe for Learning Domain-Specialized Representations
arXiv:1803.09901v11096 citations
Originality Synthesis-oriented
AI Analysis
This work addresses the need for efficient domain-specific word embeddings for NLP practitioners, but it is incremental as it builds directly on an existing method.
The authors tackled the problem of learning domain-specialized word representations by extending the GloVe model, resulting in faster learning and improved performance on various tasks.
We present a simple extension of the GloVe representation learning model that begins with general-purpose representations and updates them based on data from a specialized domain. We show that the resulting representations can lead to faster learning and better results on a variety of tasks.