Question Directed Graph Attention Network for Numerical Reasoning over Text

09/16/2020
by   Kunlong Chen, et al.
8

Numerical reasoning over texts, such as addition, subtraction, sorting and counting, is a challenging machine reading comprehension task, since it requires both natural language understanding and arithmetic computation. To address this challenge, we propose a heterogeneous graph representation for the context of the passage and question needed for such reasoning, and design a question directed graph attention network to drive multi-step numerical reasoning over this context graph.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/15/2019

NumNet: Machine Reading Comprehension with Numerical Reasoning

Numerical reasoning, such as addition, subtraction, sorting and counting...
research
09/16/2021

Numerical reasoning in machine reading comprehension tasks: are we there yet?

Numerical reasoning based machine reading comprehension is a task that i...
research
03/01/2019

DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs

Reading comprehension has recently seen rapid progress, with systems mat...
research
07/02/2021

Heterogeneous Graph Attention Network for Multi-hop Machine Reading Comprehension

Multi-hop machine reading comprehension is a challenging task in natural...
research
08/18/2021

EviDR: Evidence-Emphasized Discrete Reasoning for Reasoning Machine Reading Comprehension

Reasoning machine reading comprehension (R-MRC) aims to answer complex q...
research
09/03/2018

A3Net: Adversarial-and-Attention Network for Machine Reading Comprehension

In this paper, we introduce Adversarial-and-attention Network (A3Net) fo...
research
03/25/2019

Knowledge Aware Conversation Generation with Explainable Reasoning on Augmented Graphs

Two types of knowledge, triples from knowledge graphs and texts from uns...

Please sign up or login with your details

Forgot password? Click here to reset