Header

UZH-Logo

Maintenance Infos

Target-Level Sentence Simplification as Controlled Paraphrasing


Kew, Tannon; Ebling, Sarah (2022). Target-Level Sentence Simplification as Controlled Paraphrasing. In: Workshop on Text Simplification, Accessibility, and Readability (TSAR-2022), Abu Dhabi, 8 December 2022.

Abstract

Automatic text simplification aims to reduce the linguistic complexity of a text in order to make it easier to understand and more accessible. However, simplified texts are consumed by a diverse array of target audiences and what might be appropriately simplified for one group of readers may differ considerably for another. In this work we investigate a novel formulation of sentence simplification as paraphrasing with controlled decoding. This approach aims to alleviate the major burden of relying on large amounts of in-domain parallel training data, while at the same time allowing for modular and adaptive simplification. According to automatic metrics, our approach performs competitively against baselines that prove more difficult to adapt to the needs of different tar- get audiences or require significant amounts of complex-simple parallel aligned data.

Abstract

Automatic text simplification aims to reduce the linguistic complexity of a text in order to make it easier to understand and more accessible. However, simplified texts are consumed by a diverse array of target audiences and what might be appropriately simplified for one group of readers may differ considerably for another. In this work we investigate a novel formulation of sentence simplification as paraphrasing with controlled decoding. This approach aims to alleviate the major burden of relying on large amounts of in-domain parallel training data, while at the same time allowing for modular and adaptive simplification. According to automatic metrics, our approach performs competitively against baselines that prove more difficult to adapt to the needs of different tar- get audiences or require significant amounts of complex-simple parallel aligned data.

Statistics

Downloads

8 downloads since deposited on 13 Feb 2023
8 downloads since 12 months
Detailed statistics

Additional indexing

Item Type:Conference or Workshop Item (Other), not_refereed, original work
Communities & Collections:06 Faculty of Arts > Institute of Computational Linguistics
Dewey Decimal Classification:000 Computer science, knowledge & systems
410 Linguistics
Language:English
Event End Date:8 December 2022
Deposited On:13 Feb 2023 16:36
Last Modified:13 Feb 2023 16:36
OA Status:Green
  • Content: Accepted Version
  • Language: English