Data-Driven Methods for Solving Algebra Word Problems

By Benjamin Robaidek, Rik Koncel-Kedziorski, Hannaneh Hajishirzi. 2018

27 citations recorded by the source corpus.

We explore contemporary, data-driven techniques for solving math word problems over recent large-scale datasets. We show that well-tuned neural equation classifiers can outperform more sophisticated models such as sequence to sequence and self-attention across these datasets. Our error analysis indicates that, while fully data driven models show some promise, semantic and world knowledge is necessary for further advances.

Subfields: Artificial Intelligence, Natural Language Processing, Prompting & Reasoning

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

In Prompting & Reasoning

Citations in the corpus

Modeling Intra-Relation in Math Word Problems with Different Functional Multi-Head Attentions (2019, methodology): “The retrieval models Jaccard and Cosine in (Robaidek et al., 2018) ﬁnd the most similar math word problem in training set under a distance metric and use its equation template to compute the result.”
Template-Based Math Word Problem Solvers with Recursive Neural Networks (2019, methodology): “One of the reasons is that LSTM and CNN are used as baseline models in (Robaidek, Koncel-Kedziorski, and Hajishirzi 2018) and may not be well optimized.”
Learning by Fixing: Solving Math Word Problems with Weak Supervision (2020, methodology): “Speciﬁcally, we experiment with two inference models: Seq2Seq with bidirectional Long Short Memory network (BiLSTM) (Wu et al. 2016) and GTS (Xie and Sun 2019), and train with four learning strategies: REINFORCE, MAPO (Liang et al. 2018), LBF, LBF-w/o-M (without memory buffer).”
The Gap of Semantic Parsing: A Survey on Automatic Math Word Problem Solvers (2018, background): “Another follow-up of DNS was proposed recently in [58].”
A Survey of Deep Learning for Mathematical Reasoning (2022, unknown): “…et al., 2014) neural networks have been successfully applied to mathematical reasoning tasks, such as math word problem solving (Wang et al., 2017), theorem proving (Yang and Deng, 2019), geometry problem solving (Robaidek et al., 2018), and math question answering (Tafjord et al., 2019).”
Tree-structured Decoding for Solving Math Word Problems (2019, methodology): “The retrieval-style models compare a question in the test set with the questions in the training set, choose the template that has the highest similarity, and then ﬁll in the numbers into the template (Upadhyay and Chang, 2017; Robaidek et al., 2018).”
Graph-to-Tree Neural Networks for Learning Structured Input-Output Translation with Applications to Semantic Parsing and Math Word Problem (2020, methodology): “However, the two signiﬁcant challenges making a Seq2Seq model ineffective in these tasks are that, i) for the nat-ural text description input, it often entails some hidden syntactic structure information such as dependency, constituency tree or even semantic structure information like AMR parsing tr”