Link to the University of Pittsburgh Homepage
Link to the University Library System Homepage Link to the Contact Us Form

Integrating Transformer and Paraphrase Rules for Sentence Simplification

Zhao, Sanqiang and Meng, Rui and He, Daqing and Andi, Saptono and Bambang, Parmanto (2018) Integrating Transformer and Paraphrase Rules for Sentence Simplification. In: Empirical Methods in Natural Language Processing, 31 Oct - 1 Nov 2018, Brussels, Belgium.

[img]
Preview
PDF
Download (377kB) | Preview

Abstract

Sentence simplification aims to reduce the complexity of a sentence while retaining its original meaning. Current models for sentence simplification adopted ideas from machine translation studies and implicitly learned simplification mapping rules from normalsimple sentence pairs. In this paper, we explore a novel model based on a multi-layer and multi-head attention architecture and we propose two innovative approaches to integrate the Simple PPDB (A Paraphrase Database for Simplification), an external paraphrase knowledge base for simplification that covers a wide range of real-world simplification rules. The experiments show that the integration provides two major benefits: (1) the integrated model outperforms multiple stateof-the-art baseline models for sentence simplification in the literature (2) through analysis of the rule utilization, the model seeks to select more accurate simplification rules. The code and models used in the paper are available at https://github.com/ Sanqiang/text_simplification.


Share

Citation/Export:
Social Networking:
Share |

Details

Item Type: Conference or Workshop Item (Paper)
Status: Published
Creators/Authors:
CreatorsEmailPitt UsernameORCID
Zhao, Sanqiangsanqiang.zhao@pitt.edusaz31
Meng, Ruirui.meng@pitt.edurum20
He, Daqingdaqing@pitt.edudah44
Andi, Saptonoans38@pitt.eduans38
Bambang, Parmantoparmanto@pitt.eduparmanto
Centers: Other Centers, Institutes, or Units > Rehabilitation Engineering Research Center (RERC) on Telerehabilitation at the University of Pittsburgh
Date: 1 July 2018
Date Type: Publication
Event Title: Empirical Methods in Natural Language Processing
Event Dates: 31 Oct - 1 Nov 2018
Event Type: Conference
Schools and Programs: School of Information Sciences > Information Science
Refereed: Yes
Official URL: https://aclweb.org/anthology/papers/D/D18/D18-1355...
Date Deposited: 23 May 2019 19:16
Last Modified: 23 May 2019 19:16
URI: http://d-scholarship.pitt.edu/id/eprint/36767

Metrics

Monthly Views for the past 3 years

Plum Analytics


Actions (login required)

View Item View Item