mlsanityData to 7 Oct 2026

Investigating Math Word Problems using Pretrained Multilingual Language Models

arXiv 2105.08928 ↗First posted 19 May 2021cs.CL cs.AIcited by 21

Not on the map. Why?

Abstract (arXiv)

In this paper, we revisit math word problems~(MWPs) from the cross-lingual and multilingual perspective. We construct our MWP solvers over pretrained multilingual language models using sequence-to-sequence model with copy mechanism. We compare how the MWP solvers perform in cross-lingual and multilingual scenarios. To facilitate the comparison of cross-lingual performance, we first adapt the large-scale English dataset MathQA as a counterpart of the Chinese dataset Math23K. Then we extend several English datasets to bilingual datasets through machine translation plus human annotation. Our experiments show that the MWP solvers may not be transferred to a different language even if the target expressions have the same operator set and constants. But for both cross-lingual and multilingual cases, it can be better generalized if problem types exist on both source language and target language.

Key facts. Cited by 21 papers in the map (data through 7 Oct 2026). Builds on 18 of its 40 references that are in the map. First posted on arXiv 19 May 2021.

Builds on

18 of 40 references.

References · 18

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  3. 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,907
  4. 2019ALBERT: A Lite BERT for Self-supervised Learning of Language Representationscited by 2,772
  5. 2018XNLI: Evaluating Cross-lingual Sentence Representationscited by 913
  6. 2019MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalismscited by 653
  7. 2017Program Induction by Rationale Generation : Learning to Solve and Explain Algebraic Word Problemscited by 642
  8. 2019RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parserscited by 420
  9. 2016Solving General Arithmetic Word Problemscited by 353
  10. 2019MLQA: Evaluating Cross-lingual Extractive Question Answeringcited by 339
  11. 2019Beto, Bentz, Becas: The Surprising Cross-Lingual Effectiveness of BERTcited by 301
  12. 2016Incorporating Copying Mechanism in Sequence-to-Sequence Learningcited by 217
6 more
  1. 2018NL2Bash: A Corpus and Semantic Parser for Natural Language Interface to the Linux Operating Systemcited by 97
  2. 2018Translating a Math Word Problem to an Expression Treecited by 57
  3. 2015Program Synthesis using Natural Languagecited by 41
  4. 2020Semantically-Aligned Universal Tree-Structured Solver for Math Word Problemscited by 35
  5. 2019Program Synthesis and Semantic Parsing with Learned Code Idiomscited by 34
  6. 2017Deep Neural Machine Translation with Linear Associative Unitcited by 2

Built on by

Cited by year

Citing papers per year: 2021: 3; 2022: 7; 2023: 7; 2024: 3; 2025: 1.

21 papers.

Sort:

By area:

  1. 2024ZipCache: Accurate and Efficient KV Cache Quantization with Salient Token Identificationcited by 86
  2. 2022Learning to Reason Deductively: Math Word Problem Solving as Complex Relation Extractioncited by 44
  3. 2021MWPToolkit: An Open-Source Framework for Deep Learning-Based Math Word Problem Solverscited by 39
  4. 2021MWP-BERT: Numeracy-Augmented Pre-training for Math Word Problem Solvingcited by 32
  5. 2021Seeking Patterns, Not just Memorizing Procedures: Contrastive Learning for Solving Math Word Problemscited by 30
  6. 2023Learning by Analogy: Diverse Questions Generation in Math Word Problemcited by 18
  7. 2023MinT: Boosting Generalization in Mathematical Reasoning via Multi-View Fine-Tuningcited by 16
  8. 2022Chaining Simultaneous Thoughts for Numerical Reasoningcited by 14
  9. 2022Multi-View Reasoning: Consistent Contrastive Learning for Math Word Problemcited by 13
  10. 2023Design of Chain-of-Thought in Math Problem Solvingcited by 12
  11. 2023Numeracy from Literacy: Data Science as an Emergent Skill from Large Language Modelscited by 8
  12. 2022Analogical Math Word Problems Solving with Enhanced Problem-Solution Associationcited by 4
9 more
  1. 2023An Expression Tree Decoding Strategy for Mathematical Equation Generationcited by 4
  2. 2022Seeking Diverse Reasoning Logic: Controlled Equation Expression Generation for Solving Math Word Problemscited by 3
  3. 2023Solving Math Word Problems with Reexaminationcited by 2
  4. 2024From Large to Tiny: Distilling and Refining Mathematical Expertise for Math Word Problems with Weakly Supervisioncited by 2
  5. 2022ComSearch: Equation Searching with Combinatorial Strategy for Solving Math Word Problems with Weak Supervisioncited by 1
  6. 2022Textual Enhanced Contrastive Learning for Solving Math Word Problemscited by 1
  7. 2023Techniques to Improve Neural Math Word Problem Solverscited by 0
  8. 2024NUMCoT: Numerals and Units of Measurement in Chain-of-Thought Reasoning using Large Language Modelscited by 0
  9. 2025A Diversity-Enhanced Knowledge Distillation Model for Practical Math Word Problem Solvingcited by 0