Keywords: transfer learning, contextual embeddings, meta embeddings
TL;DR: Extract contextual embeddings from off-the-shelf supervised model. Helps downstream NLP models in low-resource settings
Abstract: Pre-trained word embeddings are the primary method for transfer learning in several Natural Language Processing (NLP) tasks. Recent works have focused on using unsupervised techniques such as language modeling to obtain these embeddings. In contrast, this work focuses on extracting representations from multiple pre-trained supervised models, which enriches word embeddings with task and domain specific knowledge. Experiments performed in cross-task, cross-domain and crosslingual settings indicate that such supervised embeddings are helpful, especially in the lowresource setting, but the extent of gains is dependent on the nature of the task and domain.