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

From the latter half of the last decade, there has been a growing interest in developing algorithms for automatically solving mathematical word problems (MWP). It is a challenging and unique task that demands blending surface level text pattern recognition with mathematical reasoning. In spite of ex...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Wiley interdisciplinary reviews. Data mining and knowledge discovery Ročník 14; číslo 4; s. e1534 - n/a
Hlavní autoři: Sundaram, Sowmya S., Gurajada, Sairam, Padmanabhan, Deepak, Abraham, Savitha Sam, Fisichella, Marco
Médium: Journal Article
Jazyk:angličtina
Vydáno: Hoboken, USA Wiley Periodicals, Inc 01.07.2024
Wiley Subscription Services, Inc
Témata:
Algorithms
automated word problem
Datasets
Deep learning
Knowledge representation
Machine learning
natural language processing
Pattern recognition
solving
Words (language)
ISSN:1942-4787, 1942-4795
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:From the latter half of the last decade, there has been a growing interest in developing algorithms for automatically solving mathematical word problems (MWP). It is a challenging and unique task that demands blending surface level text pattern recognition with mathematical reasoning. In spite of extensive research, we still have a lot to explore for building robust representations of elementary math word problems and effective solutions for the general task. In this paper, we critically examine the various models that have been developed for solving word problems, their pros and cons and the challenges ahead. In the last 2 years, a lot of deep learning models have recorded competing results on benchmark datasets, making a critical and conceptual analysis of literature highly useful at this juncture. We take a step back and analyze why, in spite of this abundance in scholarly interest, the predominantly used experiment and dataset designs continue to be a stumbling block. From the vantage point of having analyzed the literature closely, we also endeavor to provide a road‐map for future math word problem research. This article is categorized under: Technologies > Machine Learning Technologies > Artificial Intelligence Fundamental Concepts of Data and Knowledge > Knowledge Representation Math word problems are a set of controlled examples for complex semantic parsing and question answering for NLP systems. With the advent of large language models through the use of deep learning, understanding language has grown by leaps and bounds in the last couple of years. We explore the pros and cons of deep learning systems that can handle the complexity of language and math and describe the nuanced facets, the strengths and limitations.
Bibliografie:Work done while Sowmya S. Sundaram, worked at L3S Research Center, Hannover, Germany, Sairam Gurajada worked at IBM Research, Almaden, USA and Savitha Sam Abraham worked at University of Orebro, Sweden.
ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1942-4787
1942-4795
DOI:10.1002/widm.1534