Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

11-2020

Abstract

In this paper, we propose Cross-Thought, a novel approach to pre-training sequence encoder, which is instrumental in building reusable sequence embeddings for large-scale NLP tasks such as question answering. Instead of using the original signals of full sentences, we train a Transformer-based sequence encoder over a large set of short sequences, which allows the model to automatically select the most useful information for predicting masked words. Experiments on question answering and textual entailment tasks demonstrate that our pre-trained encoder can outperform state-of-the-art encoders trained with continuous sentence signals as well as traditional masked language modeling baselines. Our proposed approach also achieves new state of the art on HotpotQA (full-wiki setting) by improving intermediate information retrieval performance.

Discipline

Databases and Information Systems | Programming Languages and Compilers

Research Areas

Data Science and Engineering

Publication

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, Virtual Conference, November 16-20

First Page

412

Last Page

421

Identifier

10.18653/v1/2020.emnlp-main.30

Publisher

Association for Computational Linguistics

City or Country

Virtual Conference

Additional URL

https://arxiv.org/pdf/2010.03652.pdf

Share

COinS