Learning to Simplify Sentences with Quasi-Synchronous Grammar and Integer Programming

Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing, pages 409–420, Edinburgh, Scotland, UK, July 27–31, 2011. c⃝2011 Association for Computational Linguistics Learning to Simplify Sentences with Quasi-Synchronous Grammar and Integer Programming Kristian Woodsend and Mirella Lapata Institute for Language, Cognition and Computation School of Informatics, University of Edinburgh 10 Crichton Street, Edinburgh EH8 9AB k.woodsend@ed.ac.uk, mlap@inf.ed.ac.uk Abstract Text simplification aims to rewrite text into simpler versions, and thus make information accessible to a broader audience. Most pre- vious work simplifies sentences using hand- crafted rules aimed at splitting long sentences, or substitutes difficult words using a prede- fined dictionary. This paper presents a data- driven 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 simplifica- tion from the space of possible rewrites gen- erated by the grammar. We show experimen- tally that our method creates simplifications that significantly reduce the reading difficulty of the input, while maintaining grammaticality and preserving its meaning. 1 Introduction Sentence simplification is perhaps one of the oldest text rewriting problems. Given a source sentence, the goal is to create a grammatical target that is easier to read with simpler vocabulary and syntac- tic structure. An example is shown in Table 1 in- volving a broad spectrum of rewrite operations such as deletion, substitution, insertion, and reordering. The popularity of the simplification task stems from its potential relevance to various applications. Ex- amples include the development of reading aids for people with aphasia (Carroll et al., 1999), non-native Also contributing to the firmness in copper, the an- alyst noted, was a report by Chicago purchasing agents, which precedes the full purchasing agents re- port that is due out today and gives an indication of what the full report might hold. Also contributing to the firmness in copper, the an- alyst noted, was a report by Chicago purchasing agents. The Chicago report precedes the full purchas- ing agents report. The Chicago report gives an indica- tion of what the full report might hold. The full report is due out today. Table 1: Example of a source sentence (top) and its sim- plification (bottom). speakers (Siddharthan, 2003) and more generally in- dividuals with low literacy (Watanabe et al., 2009). A simplification component could be also used as a preprocessing step to improve the performance of parsers (Chandrasekar et al., 1996), summarizers (Beigman Klebanov et al., 2004) and semantic role labelers (Vickrey and Koller, 2008). Simplification is related to, but different from paraphrase extraction (Barzilay, 2003). We must not only have access to paraphrases (i.e., rewrite rules), but also be able to combine them to generate new text, in a simpler language. The task is also dis- tinct from sentence compression as it aims to ren- der a sentence more accessible while preserving its meaning. On the contrary, compression unavoidably leads to some information …

Content truncated to 500 words