Modeling Math Word Problems with Augmented Semantic Networks

By C. Liguda, Thies Pfeiffer. 2012

34 citations recorded by the source corpus.

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

1. Yan Wang
2. Hannaneh Hajishirzi
3. Lei Wang
4. Wei Dang Lu
5. Jian Yin
6. Chin-Yew Lin
7. Yejin Choi
8. Danqing Huang

In Natural Language Processing

1. Hannaneh Hajishirzi
2. Lei Wang
3. Yan Wang
4. Wei Dang Lu
5. Yejin Choi
6. Jierui Li
7. Jian Yin
8. Rik Koncel-Kedziorski

Citations in the corpus

• MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalisms (2019, methodology): “Solving with Handcrafted Features Due to sparsity of suitable data, early work on math word problem solving used pattern-matching to map word problems to mathematical expressions (Bobrow, 1964; Charniak, 1968, 1969), as well as non-neural statistical modeling and semantic parsing approaches (Liguda ”
• Learning to Reason Deductively: Math Word Problem Solving as Complex Relation Extraction (2022, background): “Early efforts focused on solving MWP using probabilistic models with handcrafted features (Liguda and Pfeiffer, 2012).”
• Deep Neural Solver for Math Word Problems (2017, background): “Ligu-da and Pfeiffer Liguda and Pfeiffer (2012) pro-pose modeling math word problems with augmented semantic networks.”
• How well do Computers Solve Math Word Problems? Large-Scale Dataset Construction and Evaluation (2016, background): “In symbolic approaches (Bobrow, 1964a; Bobrow, 1964b; Charniak, 1968; Charniak, 1969; Bakman, 2007; Liguda and Pfeiffer, 2012; Shi et al., 2015), math problem sentences are transformed to certain structures (usually trees) by pattern matching, verb categorization, or semantic parsing.”
• Automatically Solving Number Word Problems by Semantic Parsing and Reasoning (2015, background): “In symbolic approaches (Bobrow, 1964a, b; Charniak, 1968; Bakman, 2007; Liguda & Pfeiffer, 2012), math problem sentences are transformed to certain structures by pattern matching or verb categorization.”
• A Meaning-Based Statistical English Math Word Problem Solver (2018, background): “Mukherjee and Garain (2008) had given a good survey for all related approaches before 2008.”
• Learning Fine-Grained Expressions to Solve Math Word Problems (2017, background): “Liguda and Pfeiffer (2012) uses augmented semantic networks to represent math problems.”
• Using Intermediate Representations to Solve Math Word Problems (2018, background): “Liguda and Pfeiffer (2012) use augmented semantic network to represent math problems, where nodes represent concepts of quantities and edges represent transition states.”
• Neural Math Word Problem Solver with Reinforcement Learning (2018, methodology): “Rule-based approaches (Bobrow, 1964a; Bobrow, 1964b; Bakman, 2007; Liguda and Pfeiffer, 2012; Shi et al., 2015) accept only well formed input sentences and map them into predefined structures by rules.”