Towards Human-level Machine Reading Comprehension: Reasoning and Inference with Multiple Strategies

11/14/2017
by   Yichong Xu, et al.
0

This paper presents a new MRC model that is capable of three key comprehension skills: 1) handling rich variations in question types; 2) understanding potential answer choices; and 3) drawing inference through multiple sentences. The model is based on the proposed MUlti-Strategy Inference for Comprehension (MUSIC) architecture, which is able to dynamically apply different attention strategies to different types of questions on the fly. By incorporating a multi-step inference engine analogous to ReasoNet (Shen et al., 2017), MUSIC can also effectively perform multi-sentence inference in generating answers. Evaluation on the RACE dataset shows that the proposed method significantly outperforms previous state-of-the-art models by 7.5 relative accuracy.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/09/2017

An Empirical Analysis of Multiple-Turn Reasoning Strategies in Reading Comprehension Tasks

Reading comprehension (RC) is a challenging task that requires synthesis...
research
06/22/2020

ReCO: A Large Scale Chinese Reading Comprehension Dataset on Opinion

This paper presents the ReCO, a human-curated ChineseReading Comprehensi...
research
06/01/2023

How Many Answers Should I Give? An Empirical Study of Multi-Answer Reading Comprehension

The multi-answer phenomenon, where a question may have multiple answers ...
research
04/03/2023

Polytuplet Loss: A Reverse Approach to Training Reading Comprehension and Logical Reasoning Models

Throughout schooling, students are tested on reading comprehension and l...
research
10/31/2018

Improving Machine Reading Comprehension with General Reading Strategies

Reading strategies have been shown to improve comprehension levels, espe...
research
08/28/2018

What Makes Reading Comprehension Questions Easier?

A challenge in creating a dataset for machine reading comprehension (MRC...

Please sign up or login with your details

Forgot password? Click here to reset