Automatically Solving Number Word Problems by Semantic Parsing and Reasoning
Shuming Shi,Yuehui Wang,Chin-Yew Lin,Xiaojiang Liu,Yong Rui +4 more
- pp 1132-1142
Reads0
Chats0
TLDR
A new meaning representation language is designed to bridge natural language text and math expressions and a CFG parser is implemented based on 9,600 semi-automatically created grammar rules.Abstract:
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 semi-automatically 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.read more
Citations
More filters
Proceedings ArticleDOI
Deep Neural Solver for Math Word Problems
TL;DR: Experiments conducted on a large dataset show that the RNN model and the hybrid model significantly outperform state-of-the-art statistical learning methods for math word problem solving.
Journal ArticleDOI
Parsing Algebraic Word Problems into Equations
TL;DR: The authors use integer linear programming to generate equation trees and score their likelihood by learning local and global discriminative models, which are trained on a small set of word problems and their answers, without any manual annotation.
Proceedings ArticleDOI
MAWPS: A Math Word Problem Repository
TL;DR: MAWPS allows for the automatic construction of datasets with particular characteristics, providing tools for tuning the lexical and template overlap of a dataset as well as for filtering ungrammatical problems from web-sourced corpora.
Proceedings ArticleDOI
A Goal-Driven Tree-Structured Neural Model for Math Word Problems.
Zhipeng Xie,Shichao Sun +1 more
TL;DR: A treestructured neural model to generate expression tree in a goal-driven manner is proposed and experimental results on the dataset Math23K have shown that the model outperforms significantly several state-of-the-art models.
Proceedings ArticleDOI
How well do Computers Solve Math Word Problems? Large-Scale Dataset Construction and Evaluation
TL;DR: A large-scale dataset which is more than 9 times the size of previous ones, and contains many more problem types, and is trained to automatically extract problem answers from the answer text provided by CQA users, which significantly reduces human annotation cost.
References
More filters
Proceedings ArticleDOI
Automatic acquisition of hyponyms from large text corpora
TL;DR: A set of lexico-syntactic patterns that are easily recognizable, that occur frequently and across text genre boundaries, and that indisputably indicate the lexical relation of interest are identified.
Journal ArticleDOI
Three models for the description of language
TL;DR: It is found that no finite-state Markov process that produces symbols with transition from state to state can serve as an English grammar, and the particular subclass of such processes that produce n -order statistical approximations to English do not come closer, with increasing n, to matching the output of anEnglish grammar.
Proceedings Article
Semantic Parsing on Freebase from Question-Answer Pairs
TL;DR: This paper trains a semantic parser that scales up to Freebase and outperforms their state-of-the-art parser on the dataset of Cai and Yates (2013), despite not having annotated logical forms.
Journal ArticleDOI
Automatic labeling of semantic roles
Daniel Gildea,Dan Jurafsky +1 more
TL;DR: A system for identifying the semantic relationships, or semantic roles, filled by constituents of a sentence within a semantic frame, based on statistical classifiers trained on roughly 50,000 sentences that were hand-annotated with semantic roles by the FrameNet semantic labeling project.
Journal ArticleDOI
An efficient context-free parsing algorithm
TL;DR: In this article, a parsing algorithm which seems to be the most efficient general context-free algorithm known is described, which is similar to both Knuth's LR(k) algorithm and the familiar top-down algorithm.