@inproceedings{shardlow-przybyla-2023-simplification,
title = "Simplification by Lexical Deletion",
author = "Shardlow, Matthew and
Przyby{\l}a, Piotr",
editor = "{\v{S}}tajner, Sanja and
Saggio, Horacio and
Shardlow, Matthew and
Alva-Manchego, Fernando",
booktitle = "Proceedings of the Second Workshop on Text Simplification, Accessibility and Readability",
month = sep,
year = "2023",
address = "Varna, Bulgaria",
publisher = "INCOMA Ltd., Shoumen, Bulgaria",
url = "https://aclanthology.org/2023.tsar-1.5",
pages = "44--50",
abstract = "Lexical simplification traditionally focuses on the replacement of tokens with simpler alternatives. However, in some cases the goal of this task (simplifying the form while preserving the meaning) may be better served by removing a word rather than replacing it. In fact, we show that existing datasets rely heavily on the deletion operation. We propose supervised and unsupervised solutions for lexical deletion based on classification, end-to-end simplification systems and custom language models. We contribute a new silver-standard corpus of lexical deletions (called SimpleDelete), which we mine from simple English Wikipedia edit histories and use to evaluate approaches to detecting superfluous words. The results show that even unsupervised approaches (TerseBERT) can achieve good performance in this new task. Deletion is one part of the wider lexical simplification puzzle, which we show can be isolated and investigated.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shardlow-przybyla-2023-simplification">
<titleInfo>
<title>Simplification by Lexical Deletion</title>
</titleInfo>
<name type="personal">
<namePart type="given">Matthew</namePart>
<namePart type="family">Shardlow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Piotr</namePart>
<namePart type="family">Przybyła</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Second Workshop on Text Simplification, Accessibility and Readability</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sanja</namePart>
<namePart type="family">Štajner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Horacio</namePart>
<namePart type="family">Saggio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthew</namePart>
<namePart type="family">Shardlow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fernando</namePart>
<namePart type="family">Alva-Manchego</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>INCOMA Ltd., Shoumen, Bulgaria</publisher>
<place>
<placeTerm type="text">Varna, Bulgaria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Lexical simplification traditionally focuses on the replacement of tokens with simpler alternatives. However, in some cases the goal of this task (simplifying the form while preserving the meaning) may be better served by removing a word rather than replacing it. In fact, we show that existing datasets rely heavily on the deletion operation. We propose supervised and unsupervised solutions for lexical deletion based on classification, end-to-end simplification systems and custom language models. We contribute a new silver-standard corpus of lexical deletions (called SimpleDelete), which we mine from simple English Wikipedia edit histories and use to evaluate approaches to detecting superfluous words. The results show that even unsupervised approaches (TerseBERT) can achieve good performance in this new task. Deletion is one part of the wider lexical simplification puzzle, which we show can be isolated and investigated.</abstract>
<identifier type="citekey">shardlow-przybyla-2023-simplification</identifier>
<location>
<url>https://aclanthology.org/2023.tsar-1.5</url>
</location>
<part>
<date>2023-09</date>
<extent unit="page">
<start>44</start>
<end>50</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Simplification by Lexical Deletion
%A Shardlow, Matthew
%A Przybyła, Piotr
%Y Štajner, Sanja
%Y Saggio, Horacio
%Y Shardlow, Matthew
%Y Alva-Manchego, Fernando
%S Proceedings of the Second Workshop on Text Simplification, Accessibility and Readability
%D 2023
%8 September
%I INCOMA Ltd., Shoumen, Bulgaria
%C Varna, Bulgaria
%F shardlow-przybyla-2023-simplification
%X Lexical simplification traditionally focuses on the replacement of tokens with simpler alternatives. However, in some cases the goal of this task (simplifying the form while preserving the meaning) may be better served by removing a word rather than replacing it. In fact, we show that existing datasets rely heavily on the deletion operation. We propose supervised and unsupervised solutions for lexical deletion based on classification, end-to-end simplification systems and custom language models. We contribute a new silver-standard corpus of lexical deletions (called SimpleDelete), which we mine from simple English Wikipedia edit histories and use to evaluate approaches to detecting superfluous words. The results show that even unsupervised approaches (TerseBERT) can achieve good performance in this new task. Deletion is one part of the wider lexical simplification puzzle, which we show can be isolated and investigated.
%U https://aclanthology.org/2023.tsar-1.5
%P 44-50
Markdown (Informal)
[Simplification by Lexical Deletion](https://aclanthology.org/2023.tsar-1.5) (Shardlow & Przybyła, TSAR-WS 2023)
ACL
- Matthew Shardlow and Piotr Przybyła. 2023. Simplification by Lexical Deletion. In Proceedings of the Second Workshop on Text Simplification, Accessibility and Readability, pages 44–50, Varna, Bulgaria. INCOMA Ltd., Shoumen, Bulgaria.