Supervised Contextual Embeddings for Transfer Learning in Natural Language Processing Tasks

ICLR Workshop LLD 2019 · Mihir Kale, Aditya Siddhant, Sreyashi Nag, Radhika Parik, Matthias Grabmair, Anthony Tomasic ·

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 cross-lingual settings indicate that such supervised embeddings are helpful, especially in the low-resource setting, but the extent of gains is dependent on the nature of the task and domain. We make our code publicly available.