Open AccessPosted Content
Semantically-Aligned Equation Generation for Solving and Reasoning Math Word Problems.
Ting-Rui Chiang,Yun-Nung Chen +1 more
Reads0
Chats0
TLDR
The proposed neural math solver is based on an encoder-decoder framework, where the encoder is designed to understand the semantics of problems, and the decoder focuses on tracking semantic meanings of the generated symbols and then deciding which symbol to generate next.Abstract:
Solving math word problems is a challenging task that requires accurate natural language understanding to bridge natural language texts and math expressions. Motivated by the intuition about how human generates the equations given the problem texts, this paper presents a neural approach to automatically solve math word problems by operating symbols according to their semantic meanings in texts. This paper views the process of generating equation as a bridge between the semantic world and the symbolic world, where the proposed neural math solver is based on an encoder-decoder framework. In the proposed model, the encoder is designed to understand the semantics of problems, and the decoder focuses on tracking semantic meanings of the generated symbols and then deciding which symbol to generate next. The preliminary experiments are conducted in a dataset Math23K, and our model significantly outperforms both the state-of-the-art single model and the best non-retrieval-based model over about 10% accuracy, demonstrating the effectiveness of bridging the symbolic and semantic worlds from math word problems.read more
Citations
More filters
Proceedings Article
Chain of Thought Prompting Elicits Reasoning in Large Language Models
Jason Loh Seong Wei,Xuezhi Wang,D. Schuurmans,Maarten Bosma,Ed H. Chi,Fei Xia,Quoc Hoai Le,Denny Zhou +7 more
TL;DR: Experiments on three large language models show that chain-of-thought prompting improves performance on a range of arithmetic, commonsense, and symbolic reasoning tasks.
Journal ArticleDOI
Teaching Algorithmic Reasoning via In-context Learning
TL;DR: This article showed that it is possible to teach algorithmic reasoning to large language models via in-context learning, which they refer to as algorithmic prompting, and demonstrate significant boosts in performance over existing prompting techniques.
Proceedings ArticleDOI
Learning to Reason Deductively: Math Word Problem Solving as Complex Relation Extraction
TL;DR: This work views the task as a complex relation extraction problem, and proposes a novel approach that presents explainable deductive reasoning steps to iteratively construct target expressions, where each step involves a primitive operation over two quantities defining their relation.
Posted Content
Ape210K: A Large-Scale and Template-Rich Dataset of Math Word Problems.
TL;DR: A copy-augmented and feature-enriched sequence to sequence (seq2seq) model is proposed, which outperforms existing models by 3.2% on the Math23K dataset and serves as a strong baseline of the Ape210K dataset.
Proceedings ArticleDOI
A Survey of Deep Learning for Mathematical Reasoning
TL;DR: In this paper , the authors review the key tasks, datasets, and methods at the intersection of mathematical reasoning and deep learning over the past decade and discuss future research directions in this domain.
References
More filters
Proceedings Article
Adam: A Method for Stochastic Optimization
Diederik P. Kingma,Jimmy Ba +1 more
TL;DR: This work introduces Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments, and provides a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework.
Journal ArticleDOI
Long short-term memory
TL;DR: A novel, efficient, gradient based method called long short-term memory (LSTM) is introduced, which can learn to bridge minimal time lags in excess of 1000 discrete-time steps by enforcing constant error flow through constant error carousels within special units.
Proceedings Article
Sequence to Sequence Learning with Neural Networks
TL;DR: The authors used a multilayered Long Short-Term Memory (LSTM) to map the input sequence to a vector of a fixed dimensionality, and then another deep LSTM to decode the target sequence from the vector.
Proceedings ArticleDOI
Effective Approaches to Attention-based Neural Machine Translation
TL;DR: A global approach which always attends to all source words and a local one that only looks at a subset of source words at a time are examined, demonstrating the effectiveness of both approaches on the WMT translation tasks between English and German in both directions.
Posted Content
Neural Turing Machines
TL;DR: Neural Turing Machines as discussed by the authors extend the capabilities of neural networks by coupling them to external memory resources, which they can interact with by attentional processes, analogous to a Turing Machine or Von Neumann architecture but is differentiable end-to-end.