Learning to Simplify Sentences with Quasi-Synchronous Grammar and Integer Programming
نویسندگان
چکیده
Text simplification aims to rewrite text into simpler versions, and thus make information accessible to a broader audience. Most previous work simplifies sentences using handcrafted rules aimed at splitting long sentences, or substitutes difficult words using a predefined dictionary. This paper presents a datadriven model based on quasi-synchronous grammar, a formalism that can naturally capture structural mismatches and complex rewrite operations. We describe how such a grammar can be induced from Wikipedia and propose an integer linear programming model for selecting the most appropriate simplification from the space of possible rewrites generated by the grammar. We show experimentally that our method creates simplifications that significantly reduce the reading difficulty of the input, while maintaining grammaticality and preserving its meaning.
منابع مشابه
The Effect of Input-based and Output-based Focus on Form Instruction on Learning Grammar by Iranian EFL Learners
This quasi-experimental study investigated the effects of input-enhancement and production of sentences, containing the target structures, on learning grammar by Iranian Intermediate EFL learners. Sixty male students in three input, output, and control groups participated in the study. After checking the homogeneity of the participants with a proficiency test, the researchers administered a pre...
متن کاملTitle Generation with Quasi-Synchronous Grammar
The task of selecting information and rendering it appropriately appears in multiple contexts in summarization. In this paper we present a model that simultaneously optimizes selection and rendering preferences. The model operates over a phrase-based representation of the source document which we obtain by merging PCFG parse trees and dependency graphs. Selection preferences for individual phra...
متن کاملThe Effect of Using Mobile apps on the Acquisition of Conditional Sentences among Iranian Intermediate EFL Learners
Nowadays, there has been an increasing interest in the integration of technology in pedagogical purposes. This study was an attempt to delve in to the impact of a mobile application (Cushy Grammar) on the learning of conditional sentences (type1, 2 and 3) among Iranian intermediate EFL learners in Rooyesh institute in Isfahan. To this end, a group of 75 intermediate EFL learners were non-random...
متن کاملOnline Structured Learning for Semantic Parsing with Synchronous and λ−Synchronous Context Free Grammars
We formulate semantic parsing as a parsing problem on a synchronous context free grammar (SCFG) which is automatically built on the corpus of natural language sentences and the representation of semantic outputs. We then present an online learning framework for estimating the synchronous SCFG grammar. In addition, our online learning methods for semantic parsing problems are also extended to de...
متن کاملUofR at SemEval-2016 Task 8: Learning Synchronous Hyperedge Replacement Grammar for AMR Parsing
In this paper, we apply a synchronous-graphgrammar-based approach to SemEval-2016 Task 8, Meaning Representation Parsing. In particular, we learn Synchronous Hyperedge Replacement Grammar (SHRG) rules from aligned pairs of sentences and AMR graphs. Then we use Earley algorithm with cubepruning for AMR parsing given new sentences and the learned SHRG. Experiments on the evaluation dataset demons...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2011