Text Simplification using Typed Dependencies

A Comparision of the Robustness of Different Generation Strategies

Advaith Siddharthan

Research output: Chapter in Book/Report/Conference proceedingConference contribution

30 Citations (Scopus)

Abstract

We present a framework for text simplification based on applying transformation rules to a typed dependency representation produced by the Stanford parser. We test two approaches to regeneration from typed dependencies: (a) gen-light, where the transformed dependency graphs are linearised using the word order and morphology of the original sentence, with any changes coded into the transformation rules, and (b) gen-heavy, where the Stanford dependencies are reduced to a DSyntS representation and sentences are generating formally using the RealPro surface realiser. The main contribution of this paper is to compare the robustness of these approaches in the presence of parsing errors, using both a single parse and an n-best parse setting in an overgenerate and rank approach. We find that the gen-light approach is robust to parser error, particularly in the n-best parse setting. On the other hand, parsing errors cause the realiser in the gen-heavy approach to order words and phrases in ways that are disliked by our evaluators.
Original languageEnglish
Title of host publicationProceedings of the 13th European Workshop on Natural Language Generation
Number of pages10
Publication statusPublished - Sep 2011
Event13th European Workshop on Natural Language Generation - Nancy, France
Duration: 28 Sep 201130 Sep 2011

Conference

Conference13th European Workshop on Natural Language Generation
CountryFrance
CityNancy
Period28/09/1130/09/11

Cite this

Siddharthan, A. (2011). Text Simplification using Typed Dependencies: A Comparision of the Robustness of Different Generation Strategies. In Proceedings of the 13th European Workshop on Natural Language Generation

Text Simplification using Typed Dependencies : A Comparision of the Robustness of Different Generation Strategies. / Siddharthan, Advaith.

Proceedings of the 13th European Workshop on Natural Language Generation. 2011.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Siddharthan, A 2011, Text Simplification using Typed Dependencies: A Comparision of the Robustness of Different Generation Strategies. in Proceedings of the 13th European Workshop on Natural Language Generation. 13th European Workshop on Natural Language Generation, Nancy, France, 28/09/11.
Siddharthan A. Text Simplification using Typed Dependencies: A Comparision of the Robustness of Different Generation Strategies. In Proceedings of the 13th European Workshop on Natural Language Generation. 2011
Siddharthan, Advaith. / Text Simplification using Typed Dependencies : A Comparision of the Robustness of Different Generation Strategies. Proceedings of the 13th European Workshop on Natural Language Generation. 2011.
@inproceedings{8b36e7e0dd8d4bfba1266ce317bd22f5,
title = "Text Simplification using Typed Dependencies: A Comparision of the Robustness of Different Generation Strategies",
abstract = "We present a framework for text simplification based on applying transformation rules to a typed dependency representation produced by the Stanford parser. We test two approaches to regeneration from typed dependencies: (a) gen-light, where the transformed dependency graphs are linearised using the word order and morphology of the original sentence, with any changes coded into the transformation rules, and (b) gen-heavy, where the Stanford dependencies are reduced to a DSyntS representation and sentences are generating formally using the RealPro surface realiser. The main contribution of this paper is to compare the robustness of these approaches in the presence of parsing errors, using both a single parse and an n-best parse setting in an overgenerate and rank approach. We find that the gen-light approach is robust to parser error, particularly in the n-best parse setting. On the other hand, parsing errors cause the realiser in the gen-heavy approach to order words and phrases in ways that are disliked by our evaluators.",
author = "Advaith Siddharthan",
year = "2011",
month = "9",
language = "English",
booktitle = "Proceedings of the 13th European Workshop on Natural Language Generation",

}

TY - GEN

T1 - Text Simplification using Typed Dependencies

T2 - A Comparision of the Robustness of Different Generation Strategies

AU - Siddharthan, Advaith

PY - 2011/9

Y1 - 2011/9

N2 - We present a framework for text simplification based on applying transformation rules to a typed dependency representation produced by the Stanford parser. We test two approaches to regeneration from typed dependencies: (a) gen-light, where the transformed dependency graphs are linearised using the word order and morphology of the original sentence, with any changes coded into the transformation rules, and (b) gen-heavy, where the Stanford dependencies are reduced to a DSyntS representation and sentences are generating formally using the RealPro surface realiser. The main contribution of this paper is to compare the robustness of these approaches in the presence of parsing errors, using both a single parse and an n-best parse setting in an overgenerate and rank approach. We find that the gen-light approach is robust to parser error, particularly in the n-best parse setting. On the other hand, parsing errors cause the realiser in the gen-heavy approach to order words and phrases in ways that are disliked by our evaluators.

AB - We present a framework for text simplification based on applying transformation rules to a typed dependency representation produced by the Stanford parser. We test two approaches to regeneration from typed dependencies: (a) gen-light, where the transformed dependency graphs are linearised using the word order and morphology of the original sentence, with any changes coded into the transformation rules, and (b) gen-heavy, where the Stanford dependencies are reduced to a DSyntS representation and sentences are generating formally using the RealPro surface realiser. The main contribution of this paper is to compare the robustness of these approaches in the presence of parsing errors, using both a single parse and an n-best parse setting in an overgenerate and rank approach. We find that the gen-light approach is robust to parser error, particularly in the n-best parse setting. On the other hand, parsing errors cause the realiser in the gen-heavy approach to order words and phrases in ways that are disliked by our evaluators.

M3 - Conference contribution

BT - Proceedings of the 13th European Workshop on Natural Language Generation

ER -