Towards Question Format Independent Numerical Reasoning: A Set of Prerequisite Tasks

Abstract

Numerical reasoning is often important to accurately understand the world. Recently, several format-specific datasets have been proposed, such as numerical reasoning in the settings of Natural Language Inference (NLI), Reading Comprehension (RC), and Question Answering (QA). Several format-specific models and architectures in response to those datasets have also been proposed. However, there exists a strong need for a benchmark which can evaluate the abilities of models, in performing question format independent numerical reasoning, as (i) the numerical reasoning capabilities we want to teach are not controlled by question formats, (ii) for numerical reasoning technology to have the best possible application, it must be able to process language and reason in a way that is not exclusive to a single format, task, dataset or domain. In pursuit of this goal, we introduce NUMBERGAME, a multifaceted benchmark to evaluate model performance across numerical reasoning tasks of eight diverse formats. We add four existing question types in our compilation. Two of the new types we add are about questions that require external numerical knowledge, commonsense knowledge and domain knowledge. For building a more practical numerical reasoning system, NUMBERGAME demands four capabilities beyond numerical reasoning: (i) detecting question format directly from data (ii) finding intermediate common format to which every format can be converted (iii) incorporating commonsense knowledge (iv) handling data imbalance across formats. We build several baselines, including a new model based on knowledge hunting using a cheatsheet. However, all baselines perform poorly in contrast to the human baselines, indicating the hardness of our benchmark. Our work takes forward the recent progress in generic system development, demonstrating the scope of these under-explored tasks.

10 pages

References in corpus (7)

• MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalisms
• DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs
• Analysing Mathematical Reasoning Abilities of Neural Models
• Unit Dependency Graph and its Application to Arithmetic Word Problem Solving
• ORB: An Open Reading Benchmark for Comprehensive Evaluation of Machine Reading Comprehension
• Solving General Arithmetic Word Problems
• NumNet: Machine Reading Comprehension with Numerical Reasoning

Cited by in corpus (5)

• Investigating the Limitations of Transformers with Simple Arithmetic Tasks
• Sequence to General Tree: Knowledge-Guided Geometry Word Problem Solving
• Investigating Numeracy Learning Ability of a Text-to-Text Transfer Model
• Development of User-friendly Smart Grid Architecture
• Interviewer-Candidate Role Play: Towards Developing Real-World NLP Systems