DeepAI AI Chat
Log In Sign Up

AdaLoGN: Adaptive Logic Graph Network for Reasoning-Based Machine Reading Comprehension

03/16/2022
by   Xiao Li, et al.
Nanjing University
9

Recent machine reading comprehension datasets such as ReClor and LogiQA require performing logical reasoning over text. Conventional neural models are insufficient for logical reasoning, while symbolic reasoners cannot directly apply to text. To meet the challenge, we present a neural-symbolic approach which, to predict an answer, passes messages over a graph representing logical relations between text units. It incorporates an adaptive logic graph network (AdaLoGN) which adaptively infers logical relations to extend the graph and, essentially, realizes mutual and iterative reinforcement between neural and symbolic reasoning. We also implement a novel subgraph-to-node message passing mechanism to enhance context-option interaction for answering multiple-choice questions. Our approach shows promising results on ReClor and LogiQA.

READ FULL TEXT

page 1

page 2

page 3

page 4

10/15/2019

NumNet: Machine Reading Comprehension with Numerical Reasoning

Numerical reasoning, such as addition, subtraction, sorting and counting...
05/02/2022

Logiformer: A Two-Branch Graph Transformer Network for Interpretable Logical Reasoning

Machine reading comprehension has aroused wide concerns, since it explor...
02/11/2020

ReClor: A Reading Comprehension Dataset Requiring Logical Reasoning

Recent powerful pre-trained language models have achieved remarkable per...
07/16/2020

LogiQA: A Challenge Dataset for Machine Reading Comprehension with Logical Reasoning

Machine reading is a fundamental task for testing the capability of natu...
04/21/2020

Logic-Guided Data Augmentation and Regularization for Consistent Question Answering

Many natural language questions require qualitative, quantitative or log...
05/21/2021

Fact-driven Logical Reasoning

Logical reasoning, which is closely related to human cognition, is of vi...
07/06/2021

Improving Coherence and Consistency in Neural Sequence Models with Dual-System, Neuro-Symbolic Reasoning

Human reasoning can often be understood as an interplay between two syst...