Supervised Contextual Embeddings for Transfer Learning in Natural Language Processing Tasks
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.
Cite
Text
Kale et al. "Supervised Contextual Embeddings for Transfer Learning in Natural Language Processing Tasks." ICLR 2019 Workshops: LLD, 2019.Markdown
[Kale et al. "Supervised Contextual Embeddings for Transfer Learning in Natural Language Processing Tasks." ICLR 2019 Workshops: LLD, 2019.](https://mlanthology.org/iclrw/2019/kale2019iclrw-supervised/)BibTeX
@inproceedings{kale2019iclrw-supervised,
title = {{Supervised Contextual Embeddings for Transfer Learning in Natural Language Processing Tasks}},
author = {Kale, Mihir and Siddhant, Aditya and Nag, Sreyashi and Parik, Radhika and Tomasic, Anthony and Grabmair, Matthias},
booktitle = {ICLR 2019 Workshops: LLD},
year = {2019},
url = {https://mlanthology.org/iclrw/2019/kale2019iclrw-supervised/}
}