id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
work_7kttx52hpfgffkvvc235rluscq	Rik Koncel-Kedziorski	Parsing Algebraic Word Problems into Equations	2015	13	.pdf	application/pdf	9017	999	70	Previous work coped with the open-domain aspect of algebraic word problems by relying on deterministic state transitions based on verb categorization (Hosseini et al., 2014) or by learning templates called a Quantified Set or Qset to model natural language text quantities and their properties (e.g., '375 and combining quantities when learning the correspondence between equation trees and text. Inference (word problem w, local set relation model Llocal , global equation model Gglobal ): an ILP-based optimization method to combine extracted Qsets into a list of type-consistent candidate scores equation trees based on the global problem We use an ILP optimization model to generate equation trees involving n base Qsets. desirable candidate equations for a given word problem w using an ILP, which models global considerations such as type consistency and appropriate low models to compute a score for each candidate equation tree generated for an unseen word problem at versus the template-based method on single-equation algebra word problems.	./cache/work_7kttx52hpfgffkvvc235rluscq.pdf	./txt/work_7kttx52hpfgffkvvc235rluscq.txt