Recall and Learn: A Memory-augmented Solver for Math Word Problems
- URL: http://arxiv.org/abs/2109.13112v1
- Date: Mon, 27 Sep 2021 14:59:08 GMT
- Title: Recall and Learn: A Memory-augmented Solver for Math Word Problems
- Authors: Shifeng Huang, Jiawei Wang, Jiao Xu, Da Cao, Ming Yang
- Abstract summary: We propose a novel human-like analogical learning method in a recall and learn manner.
Our proposed framework is composed of modules of memory, representation, analogy, and reasoning.
- Score: 15.550156292329229
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: In this article, we tackle the math word problem, namely, automatically
answering a mathematical problem according to its textual description. Although
recent methods have demonstrated their promising results, most of these methods
are based on template-based generation scheme which results in limited
generalization capability. To this end, we propose a novel human-like
analogical learning method in a recall and learn manner. Our proposed framework
is composed of modules of memory, representation, analogy, and reasoning, which
are designed to make a new exercise by referring to the exercises learned in
the past. Specifically, given a math word problem, the model first retrieves
similar questions by a memory module and then encodes the unsolved problem and
each retrieved question using a representation module. Moreover, to solve the
problem in a way of analogy, an analogy module and a reasoning module with a
copy mechanism are proposed to model the interrelationship between the problem
and each retrieved question. Extensive experiments on two well-known datasets
show the superiority of our proposed algorithm as compared to other
state-of-the-art competitors from both overall performance comparison and
micro-scope studies.
Related papers
- The Function-Representation Model of Computation [2.5069344340760713]
We propose a novel model of computation, one where memory and program are merged: the Function-Representation.
This model of computation involves defining a generic Function-Representation and instantiating multiple instances of it.
We also explore the kind of functions a Function-Representation can implement, and present different ways to organise multiple instances of a Function-Representation.
arXiv Detail & Related papers (2024-10-10T13:54:35Z) - Large Language Models as Analogical Reasoners [155.9617224350088]
Chain-of-thought (CoT) prompting for language models demonstrates impressive performance across reasoning tasks.
We introduce a new prompting approach, analogical prompting, designed to automatically guide the reasoning process of large language models.
arXiv Detail & Related papers (2023-10-03T00:57:26Z) - SCREWS: A Modular Framework for Reasoning with Revisions [58.698199183147935]
We present SCREWS, a modular framework for reasoning with revisions.
We show that SCREWS unifies several previous approaches under a common framework.
We evaluate our framework with state-of-the-art LLMs on a diverse set of reasoning tasks.
arXiv Detail & Related papers (2023-09-20T15:59:54Z) - Models and algorithms for simple disjunctive temporal problems [0.8793721044482611]
We focus on the case where events may have an arbitrarily large number of release and due dates.
We provide three mathematical models to describe this problem using constraint programming and linear programming.
We implement algorithms from the literature and provide the first in-depth empirical study comparing methods to solve simple disjunctive temporal problems.
arXiv Detail & Related papers (2023-02-06T09:40:24Z) - Towards a Holistic Understanding of Mathematical Questions with
Contrastive Pre-training [65.10741459705739]
We propose a novel contrastive pre-training approach for mathematical question representations, namely QuesCo.
We first design two-level question augmentations, including content-level and structure-level, which generate literally diverse question pairs with similar purposes.
Then, to fully exploit hierarchical information of knowledge concepts, we propose a knowledge hierarchy-aware rank strategy.
arXiv Detail & Related papers (2023-01-18T14:23:29Z) - A Unified Analysis of Dynamic Interactive Learning [5.474944738795308]
Previous work by Emamjomeh-Zadeh et al. [ 2020] introduced dynamics into interactive learning as a way to model non-static user preferences.
We give a framework that captures both of the models analyzed by [Emamjomeh-Zadeh et al., 2020], which allows us to study any type of concept evolution.
We also study an efficient algorithm where the learner simply follows the feedback at each round.
arXiv Detail & Related papers (2022-04-14T16:03:37Z) - Seeking Patterns, Not just Memorizing Procedures: Contrastive Learning
for Solving Math Word Problems [14.144577791030853]
We investigate how a neural network understands patterns only from semantics.
We propose a contrastive learning approach, where the neural network perceives the divergence of patterns.
Our method greatly improves the performance in monolingual and multilingual settings.
arXiv Detail & Related papers (2021-10-16T04:03:47Z) - SMART: A Situation Model for Algebra Story Problems via Attributed
Grammar [74.1315776256292]
We introduce the concept of a emphsituation model, which originates from psychology studies to represent the mental states of humans in problem-solving.
We show that the proposed model outperforms all previous neural solvers by a large margin while preserving much better interpretability.
arXiv Detail & Related papers (2020-12-27T21:03:40Z) - Marginal likelihood computation for model selection and hypothesis
testing: an extensive review [66.37504201165159]
This article provides a comprehensive study of the state-of-the-art of the topic.
We highlight limitations, benefits, connections and differences among the different techniques.
Problems and possible solutions with the use of improper priors are also described.
arXiv Detail & Related papers (2020-05-17T18:31:58Z) - Machine Number Sense: A Dataset of Visual Arithmetic Problems for
Abstract and Relational Reasoning [95.18337034090648]
We propose a dataset, Machine Number Sense (MNS), consisting of visual arithmetic problems automatically generated using a grammar model--And-Or Graph (AOG)
These visual arithmetic problems are in the form of geometric figures.
We benchmark the MNS dataset using four predominant neural network models as baselines in this visual reasoning task.
arXiv Detail & Related papers (2020-04-25T17:14:58Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.