Results 1  10
of
13
Learning to Solve Arithmetic Word Problems with Verb Categorization
"... This paper presents a novel approach to learning to solve simple arithmetic word problems. Our system, ARIS, analyzes each of the sentences in the problem statement to identify the relevant variables and their values. ARIS then maps this information into an equation that represents the problem, an ..."
Abstract

Cited by 11 (3 self)
 Add to MetaCart
(Show Context)
This paper presents a novel approach to learning to solve simple arithmetic word problems. Our system, ARIS, analyzes each of the sentences in the problem statement to identify the relevant variables and their values. ARIS then maps this information into an equation that represents the problem, and enables its (trivial) solution as shown in Figure 1. The paper analyzes the arithmeticword problems “genre”, identifying seven categories of verbs used in such problems. ARIS learns to categorize verbs with 81.2 % accuracy, and is able to solve 77.7 % of the problems in a corpus of standard primary school test questions. We report the first learning results on this task without reliance on predefined templates and make our data publicly available.1
Language understanding for textbased games using deep reinforcement learning
 In Proceedings of the Conference on Empirical Methods in Natural Language Processing
, 2015
"... In this paper, we consider the task of learning control policies for textbased games. In these games, all interactions in the virtual world are through text and the underlying state is not observed. The resulting language barrier makes such environments challenging for automatic game players. ..."
Abstract

Cited by 4 (0 self)
 Add to MetaCart
(Show Context)
In this paper, we consider the task of learning control policies for textbased games. In these games, all interactions in the virtual world are through text and the underlying state is not observed. The resulting language barrier makes such environments challenging for automatic game players. We employ a deep reinforcement learning framework to jointly learn state representations and action policies using game rewards as feedback. This framework enables us to map text descriptions into vector representations that capture the semantics of the game states. We evaluate our approach on two game worlds, comparing against baselines using bagofwords and bagofbigrams for state representations. Our algorithm outperforms the baselines on both worlds demonstrating the importance of learning expressive representations. 1 1
Modeling Biological Processes for Reading Comprehension
, 2014
"... Machine reading calls for programs that read and understand text, but most current work only attempts to extract facts from redundant webscale corpora. In this paper, we focus on a new reading comprehension task that requires complex reasoning over a single document. The input is a paragraph descr ..."
Abstract

Cited by 4 (0 self)
 Add to MetaCart
(Show Context)
Machine reading calls for programs that read and understand text, but most current work only attempts to extract facts from redundant webscale corpora. In this paper, we focus on a new reading comprehension task that requires complex reasoning over a single document. The input is a paragraph describing a biological process, and the goal is to answer questions that require an understanding of the relations between entities and events in the process. To answer the questions, we first predict a rich structure representing the process in the paragraph. Then, we map the question to a formal query, which is executed against the predicted structure. We demonstrate that answering questions via predicted structures substantially improves accuracy over baselines that use shallower representations.
Reasoning about Quantities in Natural Language
"... Little work from the Natural Language Processing community has targeted the role of quantities in Natural Language Understanding. This paper takes some key steps towards facilitating reasoning about quantities expressed in natural language. We investigate two different tasks of numerical reasoning. ..."
Abstract

Cited by 3 (1 self)
 Add to MetaCart
(Show Context)
Little work from the Natural Language Processing community has targeted the role of quantities in Natural Language Understanding. This paper takes some key steps towards facilitating reasoning about quantities expressed in natural language. We investigate two different tasks of numerical reasoning. First, we consider Quantity Entailment, a new task formulated to understand the role of quantities in general textual inference tasks. Second, we consider the problem of automatically understanding and solving elementary school math word problems. In order to address these quantitative reasoning problems we first develop a computational approach which we show to successfully recognize and normalize textual expressions of quantities. We then use these capabilities to further develop algorithms to assist reasoning in the context of the aforementioned tasks. 1
Automatically Solving Number Word Problems by Semantic Parsing and Reasoning
"... This paper presents a semantic parsing and reasoning approach to automatically solving math word problems. A new meaning representation language is designed to bridge natural language text and math expressions. A CFG parser is implemented based on 9,600 semiautomatically created grammar rules. W ..."
Abstract

Cited by 1 (0 self)
 Add to MetaCart
(Show Context)
This paper presents a semantic parsing and reasoning approach to automatically solving math word problems. A new meaning representation language is designed to bridge natural language text and math expressions. A CFG parser is implemented based on 9,600 semiautomatically created grammar rules. We conduct experiments on a test set of over 1,500 number word problems (i.e., verbally expressed number problems) and yield 95.4 % precision and 60.2 % recall. 1
DRAW: A Challenging and Diverse Algebra Word Problem Set
"... Abstract We present DRAW, a dataset consisting of 1000 algebra word problems, semiautomatically annotated for the evaluation of automatic solvers. 1 Details of the annotation process are described, which involves a novel template reconciliation procedure for reducing equivalent templates. DRAW also ..."
Abstract
 Add to MetaCart
(Show Context)
Abstract We present DRAW, a dataset consisting of 1000 algebra word problems, semiautomatically annotated for the evaluation of automatic solvers. 1 Details of the annotation process are described, which involves a novel template reconciliation procedure for reducing equivalent templates. DRAW also consists of richer annotations, including gold coefficient alignments and equation system templates, which were absent in existing benchmarks. We present a quantitative comparison of DRAW to existing benchmarks, showing that DRAW consists a wide variety of problems, both in terms of narrative diversity and problem types. We provide a strong baseline for DRAW using a simple yet powerful solver. We also experimentally verify that the additional annotations indeed improves the performance for our automatic solver.
Combining Retrieval, Statistics, and Inference to Answer Elementary Science Questions
"... What capabilities are required for an AI system to pass standard 4th Grade Science Tests? Previous work has examined the use of Markov Logic Networks (MLNs) to represent the requisite background knowledge and interpret test questions, but did not improve upon an information retrieval (IR) baseline. ..."
Abstract
 Add to MetaCart
(Show Context)
What capabilities are required for an AI system to pass standard 4th Grade Science Tests? Previous work has examined the use of Markov Logic Networks (MLNs) to represent the requisite background knowledge and interpret test questions, but did not improve upon an information retrieval (IR) baseline. In this paper, we describe an alternative approach that operates at three levels of representation and reasoning: information retrieval, corpus statistics, and simple inference over a semiautomatically constructed knowledge base, to achieve substantially improved results. We evaluate the methods on six years of unseen, unedited exam questions from the NY Regents Science Exam (using only nondiagram, multiple choice questions), and show that our overall system’s score is 71.3%, an improvement of 23.8 % (absolute) over the MLNbased method described in previous work. We conclude with a detailed analysis, illustrating the complementary strengths of each method in the ensemble. Our datasets are being released to enable further research.
A Strong Lexical Matching Method for the Machine Comprehension Test
"... Abstract Machine comprehension of text is the overarching goal of a great deal of research in natural language processing. The Machine Comprehension Test ..."
Abstract
 Add to MetaCart
(Show Context)
Abstract Machine comprehension of text is the overarching goal of a great deal of research in natural language processing. The Machine Comprehension Test
Learn to Solve Algebra Word Problems Using Quadratic Programming
"... This paper presents a new algorithm to automatically solve algebra word problems. Our algorithm solves a word problem via analyzing a hypothesis space containing all possible equation systems generated by assigning the numbers in the word problem into a set of equation system templates extracte ..."
Abstract
 Add to MetaCart
(Show Context)
This paper presents a new algorithm to automatically solve algebra word problems. Our algorithm solves a word problem via analyzing a hypothesis space containing all possible equation systems generated by assigning the numbers in the word problem into a set of equation system templates extracted from the training data. To obtain a robust decision surface, we train a loglinear model to make the margin between the correct assignments and the false ones as large as possible. This results in a quadratic programming (QP) problem which can be efficiently solved. Experimental results show that our algorithm achieves 79.7 % accuracy, about 10 % higher than the stateoftheart baseline (Kushman et al., 2014). 1
Solving General Arithmetic Word Problems
"... Abstract This paper presents a novel approach to automatically solving arithmetic word problems. This is the first algorithmic approach that can handle arithmetic problems with multiple steps and operations, without depending on additional annotations or predefined templates. We develop a theory fo ..."
Abstract
 Add to MetaCart
(Show Context)
Abstract This paper presents a novel approach to automatically solving arithmetic word problems. This is the first algorithmic approach that can handle arithmetic problems with multiple steps and operations, without depending on additional annotations or predefined templates. We develop a theory for expression trees that can be used to represent and evaluate the target arithmetic expressions; we use it to uniquely decompose the target arithmetic problem to multiple classification problems; we then compose an expression tree, combining these with world knowledge through a constrained inference framework. Our classifiers gain from the use of quantity schemas that supports better extraction of features. Experimental results show that our method outperforms existing systems, achieving state of the art performance on benchmark datasets of arithmetic word problems.