DeepAI AI Chat
Log In Sign Up

Discrete Reasoning Templates for Natural Language Understanding

by   Hadeel Al-Negheimish, et al.

Reasoning about information from multiple parts of a passage to derive an answer is an open challenge for reading-comprehension models. In this paper, we present an approach that reasons about complex questions by decomposing them to simpler subquestions that can take advantage of single-span extraction reading-comprehension models, and derives the final answer according to instructions in a predefined reasoning template. We focus on subtraction-based arithmetic questions and evaluate our approach on a subset of the DROP dataset. We show that our approach is competitive with the state-of-the-art while being interpretable and requires little supervision


page 1

page 2

page 3

page 4


R3: A Reading Comprehension Benchmark Requiring Reasoning Processes

Existing question answering systems can only predict answers without exp...

What Makes Reading Comprehension Questions Easier?

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

Giving BERT a Calculator: Finding Operations and Arguments with Reading Comprehension

Reading comprehension models have been successfully applied to extractiv...

Machine Reading, Fast and Slow: When Do Models "Understand" Language?

Two of the most fundamental challenges in Natural Language Understanding...

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

Reasoning machine reading comprehension (R-MRC) aims to answer complex q...

Assessing the Benchmarking Capacity of Machine Reading Comprehension Datasets

Existing analysis work in machine reading comprehension (MRC) is largely...

RC-QED: Evaluating Natural Language Derivations in Multi-Hop Reading Comprehension

Recent studies revealed that reading comprehension (RC) systems learn to...