Learning to Solve Arithmetic Word Problems with Verb Categorization

This paper presents a novel approach to learning to solve simple arithmetic word problems. Our system, ARIS, analyzes each of the sentences in the problem statement to identify the relevant variables and their values. ARIS then maps this information into an equation that represents the problem, and enables its (trivial) solution as shown in Figure 1. The paper analyzes the arithmetic-word problems “genre”, identifying seven categories of verbs used in such problems. ARIS learns to categorize verbs with 81.2% accuracy, and is able to solve 77.7% of the problems in a corpus of standard primary school test questions. We report the first learning results on this task without reliance on predefined templates and make our data publicly available. 1

• Publication year

  2014

• Venue

  Conference on Empirical Methods in Natural Language Processing

• Publication date

  2014-10-01

• Fields of study

  Mathematics, Computer Science

• Identifiers
  DOI 10.3115/v1/D14-1058
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Training a Multilingual Sportscaster: Using Perceptual Context to Learn Language

  2014cited by this paper
• Learning to Automatically Solve Algebra Word Problems

  2014influential reference
• Using Semantic Unification to Generate Regular Expressions from Natural Language

  2013cited by this paper
• Joint Coreference Resolution and Named-Entity Linking with Multi-Pass Sieves

  2013cited by this paper
• Obituary: George A. Miller

  2013cited by this paper
• Learning High-Level Planning from Text

  2012cited by this paper
• Semantic Understanding of Professional Soccer Commentaries

  2012cited by this paper
• Confidence Driven Unsupervised Semantic Parsing

  2011cited by this paper
• Reasoning about RoboCup Soccer Narratives

  2011cited by this paper
• A Multi-Pass Sieve for Coreference Resolution

  2010cited by this paper
• Training a multilingual sportscaster

  2010cited by this paper
• Label Ranking under Ambiguous Supervision for Learning Semantic Correspondences

  2010cited by this paper
• Learning to Follow Navigational Directions

  2010cited by this paper
• Unsupervised Semantic Parsing

  2009cited by this paper
• Reinforcement Learning for Mapping Instructions to Actions

  2009cited by this paper
• Unsupervised Learning of Narrative Schemas and their Participants

  2009cited by this paper
• Reading to Learn: Constructing Features from Semantic Abstracts

  2009cited by this paper
• Learning Semantic Correspondences with Less Supervision

  2009cited by this paper
• Packed computation of exact meaning representations

  2007cited by this paper
• L1‐regularization path algorithm for generalized linear models

  2007cited by this paper
• Learning Language Semantics from Ambiguous Supervision

  2007cited by this paper
• Database-Text Alignment via Structured Multilabel Classification

  2007cited by this paper
• Discriminative Reranking for Semantic Parsing

  2006cited by this paper
• Generating Typed Dependency Parses from Phrase Structure Parses

  2006cited by this paper
• Learning to Map Sentences to Logical Form: Structured Classification with Probabilistic Categorial Grammars

  2005cited by this paper
• Incorporating Non-local Information into Information Extraction Systems by Gibbs Sampling

  2005cited by this paper
• Solving logic puzzles: From robust processing to precise semantics

  2004cited by this paper
• Weka: Practical machine learning tools and techniques with Java implementations

  1999cited by this paper
• An Information-Theoretic Definition of Similarity

  1998cited by this paper
• WordNet: A Lexical Database for English

  1995cited by this paper
• Circumscription: a form of non-monotonic reasoning

  1995cited by this paper
• Using Information Content to Evaluate Semantic Similarity in a Taxonomy

  1995cited by this paper
• Circumscription - A Form of Non-Monotonic Reasoning

  1980cited by this paper
• Circumscription|a Form of Nonmonotonic Reasoning

  1979cited by this paper
• Computers and Thought

  1963cited by this paper

• Nonlinearity as Rank: Generative Low-Rank Adapter with Radial Basis Functions

  2026cites this paper
• CoMoL: Efficient Mixture of LoRA Experts via Dynamic Core Space Merging

  2026cites this paper
• Chain-of-thought driven dynamic prompting and computation method

  2026cites this paper
• IVC-DB: Iterative verification correction method guided by dual-Backward mathematical reasoning in large language models

  2026cites this paper
• BenNumEval: A Benchmark to Assess LLMs' Numerical Reasoning Capabilities in Bengali

  2025cites this paper
• On the Generalization vs Fidelity Paradox in Knowledge Distillation

  2025cites this paper
• Exploring Backward Reasoning in Large Language Models

  2025cites this paper
• BanglaMATH : A Bangla benchmark dataset for testing LLM mathematical reasoning at grades 6, 7, and 8

  2025cites this paper
• AgenticMath: Enhancing LLM Reasoning via Agentic-based Math Data Generation

  2025cites this paper
• Error Classification of Large Language Models on Math Word Problems: A Dynamically Adaptive Framework

  2025cites this paper
• Dynamic Collaboration of Multi-Language Models based on Minimal Complete Semantic Units

  2025cites this paper
• Failures Are the Stepping Stones to Success: Enhancing Few-Shot In-Context Learning by Leveraging Negative Samples

  2025cites this paper
• Learning Distribution-Wise Control in Representation Space for Language Models

  2025cites this paper
• Skip-Thinking: Chunk-wise Chain-of-Thought Distillation Enable Smaller Language Models to Reason Better and Faster

  2025cites this paper
• STITCH: Simultaneous Thinking and Talking with Chunked Reasoning for Spoken Language Models

  2025cites this paper
• MoEs Are Stronger than You Think: Hyper-Parallel Inference Scaling with RoE

  2025cites this paper
• UORA: Uniform Orthogonal Reinitialization Adaptation in Parameter-Efficient Fine-Tuning of Large Models

  2025cites this paper
• Implicit Reasoning in Large Language Models: A Comprehensive Survey

  2025cites this paper
• A Comparative Analysis of Sparse Autoencoder and Activation Difference in Language Model Steering

  2025cites this paper
• Benchmarking State-of-the-Art Math Word Problem Solvers on Arabic Data

  2025cites this paper
• A diversity-enhanced knowledge distillation model for practical math word problem solving

  2025cites this paper
• TAPO: Task-Referenced Adaptation for Prompt Optimization

  2025cites this paper
• SliceFine: The Universal Winning-Slice Hypothesis for Pretrained Networks

  2025cites this paper
• Chain-of-Reasoning: Towards Unified Mathematical Reasoning in Large Language Models via a Multi-Paradigm Perspective

  2025cites this paper
• A Survey on Feedback-based Multi-step Reasoning for Large Language Models on Mathematics

  2025cites this paper
• Mini-Omni-Reasoner: Token-Level Thinking-in-Speaking in Large Speech Models

  2025cites this paper
• Deep Learning Models for Solving Financial Word Problems

  2025cites this paper
• Classification of inductive thinking in mathematical problem solving

  2025cites this paper
• A Survey on Mathematical Reasoning and Optimization with Large Language Models

  2025cites this paper
• TabularMath: Understanding Math Reasoning over Tables with Large Language Models

  2025cites this paper
• Exchange of Perspective Prompting Enhances Reasoning in Large Language Models

  2025cites this paper
• Towards Spoken Mathematical Reasoning: Benchmarking Speech-based Models over Multi-faceted Math Problems

  2025cites this paper
• Evaluating Numeracy of Language Models as a Natural Language Inference Task

  2025cites this paper
• Robustness of Prompting: Enhancing Robustness of Large Language Models Against Prompting Attacks

  2025influential citation
• Balancing Precision and Generalization: Dynamic Instruction Generation for Model Adaptive Zero-Shot Reasoning in LLMs

  2025cites this paper
• Multi-Model System for Enhanced QA: Contextual Answering, Profanity Filtering, and Pair Generation

  2025cites this paper
• Parameter-Efficient Routed Fine-Tuning: Mixture-of-Experts Demands Mixture of Adaptation Modules

  2025cites this paper
• Principled Personas: Defining and Measuring the Intended Effects of Persona Prompting on Task Performance

  2025cites this paper
• Semantic interaction-enhanced encoding network for math word problem solving

  2025cites this paper
• Toward large reasoning models: A survey of reinforced reasoning with large language models

  2025cites this paper
• Calibrating and Rotating: A Unified Framework for Weight Conditioning in PEFT

  2025cites this paper
• DiverSeed: Integrating Active Learning for Target Domain Data Generation in Instruction Tuning

  2025cites this paper
• CoMoE: Contrastive Representation for Mixture-of-Experts in Parameter-Efficient Fine-tuning

  2025cites this paper
• Understanding Before Reasoning: Enhancing Chain-of-Thought with Iterative Summarization Pre-Prompting

  2025cites this paper
• MoA: Heterogeneous Mixture of Adapters for Parameter-Efficient Fine-Tuning of Large Language Models

  2025cites this paper
• HyperAdapt: Simple High-Rank Adaptation

  2025cites this paper
• Predicting Through Generation: Why Generation Is Better for Prediction

  2025cites this paper
• A generation model of math word problem solution via kernel mean dynamic aggregation and dual-decoder synergy fusion

  2025cites this paper
• NeuroAda: Activating Each Neuron's Potential for Parameter-Efficient Fine-Tuning

  2025cites this paper
• Towards Efficient CoT Distillation: Self-Guided Rationale Selector for Better Performance with Fewer Rationales

  2025cites this paper
• Stop Overvaluing Multi-Agent Debate -- We Must Rethink Evaluation and Embrace Model Heterogeneity

  2025cites this paper
• CE-LoRA: Computation-Efficient LoRA Fine-Tuning for Language Models

  2025cites this paper
• Reasoning on a Spectrum: Aligning LLMs to System 1 and System 2 Thinking

  2025influential citation
• Is Depth All You Need? An Exploration of Iterative Reasoning in LLMs

  2025influential citation
• Making Large Language Models Better Reasoners with Orchestrated Streaming Experiences

  2025cites this paper
• Steering Information Utility in Key-Value Memory for Language Model Post-Training

  2025cites this paper
• BMWP: the first Bengali math word problems dataset for operation prediction and solving

  2025cites this paper
• Accuracy and creativity analysis of ChatGPT in quantitative aptitude

  2025cites this paper
• A Scene-Attention Relation-Centric Algorithm for Solving Arithmetic Word Problems

  2025cites this paper
• A Multilingual Dataset (MultiMWP) and Benchmark for Math Word Problem Generation

  2025cites this paper
• Generating Pedagogically Meaningful Visuals for Math Word Problems: A New Benchmark and Analysis of Text-to-Image Models

  2025cites this paper
• DenseLoRA: Dense Low-Rank Adaptation of Large Language Models

  2025influential citation
• CRMR: A Collaborative Multistep Reasoning Framework for Solving Mathematical Problems

  2025cites this paper
• LLM ethics benchmark: a three-dimensional assessment system for evaluating moral reasoning in large language models

  2025cites this paper
• Does a language model “understand” high school math? A survey of deep learning based word problem solvers

  2024cites this paper
• RankPrompt: Step-by-Step Comparisons Make Language Models Better Reasoners

  2024cites this paper
• ReFT: Representation Finetuning for Language Models

  2024cites this paper
• Data Augmentation with In-Context Learning and Comparative Evaluation in Math Word Problem Solving

  2024cites this paper
• Exploring the Limitations of Large Language Models in Compositional Relation Reasoning

  2024cites this paper
• FineMath: A Fine-Grained Mathematical Evaluation Benchmark for Chinese Large Language Models

  2024influential citation
• Orca-Math: Unlocking the potential of SLMs in Grade School Math

  2024cites this paper
• Improving Language Model Reasoning with Self-motivated Learning

  2024cites this paper
• Refining Answer Distributions for Improved Large Language Model Reasoning

  2024influential citation
• MoELoRA: Contrastive Learning Guided Mixture of Experts on Parameter-Efficient Fine-Tuning for Large Language Models

  2024influential citation
• FormulaReasoning: A Dataset for Formula-Based Numerical Reasoning

  2024cites this paper
• GLaPE: Gold Label-agnostic Prompt Evaluation for Large Language Models

  2024cites this paper
• RevOrder: A Novel Method for Enhanced Arithmetic in Language Models

  2024cites this paper
• Rethinking Chain-of-Thought from the Perspective of Self-Training

  2024cites this paper
• ConceptMath: A Bilingual Concept-wise Benchmark for Measuring Mathematical Reasoning of Large Language Models

  2024cites this paper
• Zero-Shot Chain-of-Thought Reasoning Guided by Evolutionary Algorithms in Large Language Models

  2024influential citation
• Distilling Reasoning Ability From Large Language Models With Adaptive Thinking

  2024cites this paper
• Enhanced Graph-Based Model with Mathematical Knowledge Embedding for Math Word Problem Solving

  2024cites this paper
• Explicit Memory Learning with Expectation Maximization

  2024cites this paper
• Subjective Topic meets LLMs: Unleashing Comprehensive, Reflective and Creative Thinking through the Negation of Negation

  2024cites this paper
• From Bottom to Top: Extending the Potential of Parameter Efficient Fine-Tuning

  2024cites this paper
• Mathematical Problem Solving in Arabic: Assessing Large Language Models

  2024cites this paper
• Persona is a Double-edged Sword: Mitigating the Negative Impact of Role-playing Prompts in Zero-shot Reasoning Tasks

  2024cites this paper
• MoS2: Mixture of Scale and Shift Experts for Text-Only Video Captioning

  2024cites this paper
• Hierarchical Attention Decoder for Solving Math Word Problems

  2024cites this paper
• Towards Goal-oriented Prompt Engineering for Large Language Models: A Survey

  2024cites this paper
• Demystifying Chains, Trees, and Graphs of Thoughts

  2024cites this paper
• Fewer is More: Boosting Math Reasoning with Reinforced Context Pruning

  2024cites this paper
• SciInstruct: a Self-Reflective Instruction Annotated Dataset for Training Scientific Language Models

  2024cites this paper
• Escape Sky-high Cost: Early-stopping Self-Consistency for Multi-step Reasoning

  2024cites this paper
• Tuning Language Models by Mixture-of-Depths Ensemble

  2024cites this paper
• A Theoretical Review on Solving Algebra Problems

  2024cites this paper
• Adaption-of-Thought: Learning Question Difficulty Improves Large Language Models for Reasoning

  2024influential citation
• Hint Marginalization for Improved Reasoning in Large Language Models

  2024influential citation
• AlphaLoRA: Assigning LoRA Experts Based on Layer Training Quality

  2024cites this paper
• RoCoFT: Efficient Finetuning of Large Language Models with Row-Column Updates

  2024cites this paper