English

Supervised Contextual Embeddings for Transfer Learning in Natural Language Processing Tasks

Computation and Language 2019-07-01 v1 Machine Learning

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 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.

Keywords

Cite

@article{arxiv.1906.12039,
  title  = {Supervised Contextual Embeddings for Transfer Learning in Natural Language Processing Tasks},
  author = {Mihir Kale and Aditya Siddhant and Sreyashi Nag and Radhika Parik and Matthias Grabmair and Anthony Tomasic},
  journal= {arXiv preprint arXiv:1906.12039},
  year   = {2019}
}

Comments

Appeared in 2nd Learning from Limited Labeled Data (LLD) Workshop at ICLR 2019

R2 v1 2026-06-23T10:06:20.315Z