Learning to Automatically Solve Algebra Word Problems

Kushman, Nate; Artzi, Yoav; Zettlemoyer, Luke; Barzilay, Regina

doi:10.3115/v1/p14-1026

Cited by 277 publications

(209 citation statements)

References 11 publications

Supporting

Mentioning

176

Contrasting

Unclassified

Order By: Relevance

“…There is a growing body of work in solving standardized tests such as reading comprehensions (Richardson et al, 2013;Sachan et al, 2015, inter alia), science question answering (Schoenick et al, 2016;Sachan et al, 2016, inter alia), algebra word problems (Kushman et al, 2014, inter alia), geometry problems (Seo et al, 2015), pre-university entrance exams (Fujita et al, 2014), etc. A major challenge in building these solvers is the lack of subject knowledge.…”

Section: Introductionmentioning

confidence: 99%

From Textbooks to Knowledge: A Case Study in Harvesting Axiomatic Knowledge from Textbooks to Solve Geometry Problems

Sachan

Dubey

Xing

2017

Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

Textbooks are rich sources of knowledge. Harvesting knowledge from textbooks is a key challenge in many educational applications. In this paper, we present an approach to obtain axiomatic knowledge of geometry in the form of horn-clause rules from math textbooks. The approach uses rich contextual and typographical features extracted from the textbooks. It also leverages the redundancy and shared ordering of axioms across multiple textbooks to accurately harvest axioms. These axioms are then parsed into horn-clause rules that are used to improve the state-of-the-art in solving geometry problems.

show abstract

Section: Introductionmentioning

confidence: 99%

From Textbooks to Knowledge: A Case Study in Harvesting Axiomatic Knowledge from Textbooks to Solve Geometry Problems

Sachan

Dubey

Xing

2017

Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

show abstract

“…However, these prior approaches have employed relatively simple semantic information from the referring expressions, such as a manually created lexicon, or have operated within an environment with a limited set of pre-defined objects. Besides reference resolution in situated dialogue, there is also a research direction in which machine learning models are used to learn the semantics of noun phrases in order to map noun phrases to objects in a related environment Liang et al, 2009;Naim et al, 2014;Kushman et al, 2014). However, these prior approaches operated at the granularity of single of the corpus utilized in this work.…”

Section: Introductionmentioning

confidence: 99%

“…Another closely related research direction involves reference resolution in physical environments Kushman et al, 2014;Naim et al, 2014;Liang et al, 2009). Although not within situated dialogue per se (because only one participant speaks), these lines of investigation have produced approaches that link natural language noun phrases to objects in an environment, such as a set of objects of different type and color on a table or a variable in a mathematical formula (Kushman et al, 2014).…”

Section: Related Workmentioning

confidence: 99%

“…Although not within situated dialogue per se (because only one participant speaks), these lines of investigation have produced approaches that link natural language noun phrases to objects in an environment, such as a set of objects of different type and color on a table or a variable in a mathematical formula (Kushman et al, 2014). Some of these learn the mapping relationship by learning the semantics of words in the referring expressions Liang et al, 2009) with referring expression-referent pairs as input.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Proceedings of the 17th Annual Meeting of the Special Interest Group on Discourse and Dialogue

Katagiri

Nakano

Fernández

et al. 2016

View full text Add to dashboard Cite

We extend special thanks to our Local co-Chairs, Ron Artstein and Alesia Gainer, and their team of student volunteers. We know SIGDIAL 2016 would not have been possible without Ron and Alesia, who invested so much effort in arranging the conference venue and accommodations, handling registration, making banquet arrangements, and handling numerous other preparations for the conference. The student volunteers for on-site assistance also deserve our appreciation.Ethan Selfridge, Sponsorships Chair, has earned our appreciation for recruiting and liaising with our conference sponsors, many of whom continue to contribute year after year. Sponsorships support valuable aspects of the program, such as the invited speakers and conference banquet. In recognition of this, we gratefully acknowledge the support of our sponsors: (Platinum level) Microsoft Research, Xerox and PARC, Intel, (Gold level) Facebook, (Silver level) Amazon Alexa, Interactions, Educational Testing Service, Honda Research Institute, and Yahoo!. At the same time, we thank Priscilla Rasmussen at the ACL for tirelessly handling the financial aspects of sponsorship for SIGDIAL 2016, and for securing our ISBN.iii We also thank the SIGdial board, especially officers Amanda Stent, Jason Williams and Kristiina Jokinen for their advice and support from beginning to end.Finally, we thank all the authors of the papers in this volume, and all the conference participants for making this stimulating event a valuable opportunity for growth in the research areas of discourse and dialogue. AbstractThis paper presents an end-to-end framework for task-oriented dialog systems using a variant of Deep Recurrent QNetworks (DRQN). The model is able to interface with a relational database and jointly learn policies for both language understanding and dialog strategy. Moreover, we propose a hybrid algorithm that combines the strength of reinforcement learning and supervised learning to achieve faster learning speed. We evaluated the proposed model on a 20 Question Game conversational game simulator. Results show that the proposed method outperforms the modular-based baseline and learns a distributed representation of the latent dialog state. IntroductionTask-oriented dialog systems have been an important branch of spoken dialog system (SDS) research (Raux et al., 2005; Young, 2006; Bohus and Rudnicky, 2003). The SDS agent has to achieve some predefined targets (e.g. booking a flight) through natural language interaction with the users. The typical structure of a task-oriented dialog system is outlined in Figure 1 (Young, 2006). This pipeline consists of several independently-developed modules: natural language understanding (the NLU) maps the user utterances to some semantic representation. This information is further processed by the dialog state tracker (DST), which accumulates the input of the turn along with the dialog history. The DST outputs the current dialog state and the dialog policy selects the next system action based on the dialog state. Then natural language gene...

show abstract

“…As discussed in our analysis, such systems cannot handle well questions involving negation and quantification. Numerical questions, which we found to be particularly challenging, have been the focus of recent work on algebra word problems (Kushman et al, 2014) for which dedicated systems have been developed. MacCartney et al (2006) demonstrated that a large set of rules can be used to recognize valid textual entailments.…”

Section: Related Workmentioning

confidence: 99%

A Strong Lexical Matching Method for the Machine Comprehension Test

Smith

Greco

Bošnjak

et al. 2015

Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

Machine comprehension of text is the overarching goal of a great deal of research in natural language processing. The Machine Comprehension Test (Richardson et al., 2013) was recently proposed to assess methods on an open-domain, extensible, and easy-to-evaluate task consisting of two datasets. In this paper we develop a lexical matching method that takes into account multiple context windows, question types and coreference resolution. We show that the proposed method outperforms the baseline of Richardson et al. (2013), and despite its relative simplicity, is comparable to recent work using machine learning. We hope that our approach will inform future work on this task. Furthermore, we argue that MC500 is harder than MC160 due to the way question answer pairs were created.

show abstract

Learning to Automatically Solve Algebra Word Problems

Cited by 277 publications

References 11 publications

From Textbooks to Knowledge: A Case Study in Harvesting Axiomatic Knowledge from Textbooks to Solve Geometry Problems

From Textbooks to Knowledge: A Case Study in Harvesting Axiomatic Knowledge from Textbooks to Solve Geometry Problems

Proceedings of the 17th Annual Meeting of the Special Interest Group on Discourse and Dialogue

A Strong Lexical Matching Method for the Machine Comprehension Test

Contact Info

Product

Resources

About