Reasoning about Quantities in Natural Language

By Subhro Roy, Tim Vieira, Dan Roth. 2015

177 citations recorded by the source corpus.

Little work from the Natural Language Processing community has targeted the role of quantities in Natural Language Understanding. This paper takes some key steps towards facilitating reasoning about quantities expressed in natural language. We investigate two different tasks of numerical reasoning. First, we consider Quantity Entailment, a new task formulated to understand the role of quantities in general textual inference tasks. Second, we consider the problem of automatically understanding and solving elementary school math word problems. In order to address these quantitative reasoning problems we first develop a computational approach which we show to successfully recognize and normalize textual expressions of quantities. We then use these capabilities to further develop algorithms to assist reasoning in the context of the aforementioned tasks.

Subfields: Artificial Intelligence, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Natural Language Processing

Citations in the corpus

Chain of Thought Prompting Elicits Reasoning in Large Language Models (2022, background): “Their work is a remarkable contrast to the literature using formal languages to reason (Roy et al., 2015; Chiang and Chen, 2019; Amini et al., 2019; Chen et al., 2019).”
MAWPS: A Math Word Problem Repository (2016, background): “• SingleOp: Collection of single operation arith- metic problems (Roy et al., 2015).”
Generate & Rank: A Multi-task Framework for Math Word Problems (2021, neutral): “Roy et al. (2015) proposes three types of classiﬁers to identify different elements of problems.”
Injecting Numerical Reasoning Skills into Language Models (2020, methodology): “All models that were ﬁne-tuned on DROP were evaluated in a zero-shot setup on 395 examples from A DD S UB (Hosseini et al., 2014), 321 from SO P (Roy et al., 2015), and 305 from SE Q (Koncel-Kedziorski et al., 2015).”
Semantically-Aligned Equation Generation for Solving and Reasoning Math Word Problems (2018, methodology): “The The results are consistent with those hand-craft features for solving math word problems proposed by the prior research (Hos-seini et al., 2014; Roy and Roth, 2015; Roy et al., 2015).”
Solving General Arithmetic Word Problems (2016, methodology): “For the IL dataset, we acquired the system of (Roy et al., 2015) from the authors, and ran it with the same fold information.”
Parsing Algebraic Word Problems into Equations (2015, background): “We have discovered, however, that both approaches are brittle, particularly as training data is scarce in this domain, and the space of equations grows exponentially with the number of quantities mentioned in the math problem.”
Stress Test Evaluation for Natural Language Inference (2018, neutral): “pected to be challenging for entailment models (Jijkoun and De Rijke, 2006; LoBue and Yates, 2011; Roy, 2017) while some others have been contemporaneously corroborated (Gururangan et al.”
Deep Neural Solver for Math Word Problems (2017, background): “In addition, Roy and Roth Roy et al. (2015); Roy and Roth (2016) tries to handle arithmetic problems with multiple steps and operations without depending on additional annotations or predeﬁned templates.”
MathDQN: Solving Arithmetic Word Problems via Deep Reinforcement Learning (2018, neutral): “IL (Roy et al. 2015).”
EQUATE: A Benchmark Evaluation Framework for Quantitative Reasoning in Natural Language Inference (2019, neutral): “ Our work bridges this gap by providing a more comprehensive examination of quantitative reasoning in NLI. While to the best of our knowledge, prior work has not studied quantitative reasoning in NLI,Roy (2017) propose a model for a related subtask called quantity entailment, which aims to determine”
Learn to Solve Algebra Word Problems Using Quadratic Programming (2015, background): “Recently, using machine learning techniques to construct the solver has become a new trend (Kushman et al., 2014; Hosseini et al., 2014; Amnueypornsakul and Bhat, 2014; Roy et al., 2015).”
Point to the Expression: Solving Algebraic Word Problems Using the Expression-Pointer Transformer Model (2020, methodology): “Other models selected operands first before constructing expression trees with operators in the second step (Roy et al., 2015; Roy and Roth, 2015).”
The Gap of Semantic Parsing: A Survey on Automatic Math Word Problem Solvers (2018, methodology): “POS tags [28] [39] [40] [45] [20] For “A chef needs to cook 16.0 potatoes.””
Representing Numbers in NLP: a Survey and a Vision (2021, methodology): “Quantity Entailment tasks (Ravichander et al., 2019; Roy et al., 2015), analogous to Natural”
A Survey of Deep Learning for Mathematical Reasoning (2022, unknown): “Early math word problem datasets are relatively small or limited to a small number of operation steps (Hosseini et al., 2014; Kushman et al., 2014; Roy et al., 2015).”
Reasoning with Language Model Prompting: A Survey (2022, background): “Early works on this task (Hosseini et al., 2014; Kushman et al., 2014; Roy et al., 2015; Koncel-Kedziorski et al., 2015; Roy and Roth, 2015) focus on relatively small datasets consist-”