Improving Machine Reading Comprehension with Single-choice Decision and Transfer Learning

Jing Gong; Mu Li; Peng Meng; Shuangzhi Wu; Weiliang Lin; Yahui Cheng; Yufan Jiang; Zhibo Chen

arxiv: 2011.03292 · v2 · pith:JY4WXO6V · submitted 2020-11-06 · cs.CL

Improving Machine Reading Comprehension with Single-choice Decision and Transfer Learning

Yufan Jiang , Shuangzhi Wu , Jing Gong , Yahui Cheng , Peng Meng , Weiliang Lin , Zhibo Chen , Mu li This is my paper

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:JY4WXO6V record.json open to challenge →

classification cs.CL

keywords modelmulti-choicesingle-choiceanswerbettercomprehensioncorrectknowledge

0 comments

read the original abstract

Multi-choice Machine Reading Comprehension (MMRC) aims to select the correct answer from a set of options based on a given passage and question. Due to task specific of MMRC, it is non-trivial to transfer knowledge from other MRC tasks such as SQuAD, Dream. In this paper, we simply reconstruct multi-choice to single-choice by training a binary classification to distinguish whether a certain answer is correct. Then select the option with the highest confidence score. We construct our model upon ALBERT-xxlarge model and estimate it on the RACE dataset. During training, We adopt AutoML strategy to tune better parameters. Experimental results show that the single-choice is better than multi-choice. In addition, by transferring knowledge from other kinds of MRC tasks, our model achieves a new state-of-the-art results in both single and ensemble settings.

This paper has not been read by Pith yet.

discussion (0)

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

Using DeepSpeed and Megatron to Train Megatron-Turing NLG 530B, A Large-Scale Generative Language Model
cs.CL 2022-01 unverdicted novelty 5.0

Trained the largest monolithic 530B-parameter transformer language model to date and reported new state-of-the-art zero- and few-shot results on multiple NLP benchmarks.