@inproceedings{ribeiro-etal-2023-generating,
title = "Generating Summaries with Controllable Readability Levels",
author = "Ribeiro, Leonardo F. R. and
Bansal, Mohit and
Dreyer, Markus",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.emnlp-main.714",
doi = "10.18653/v1/2023.emnlp-main.714",
pages = "11669--11687",
abstract = "Readability refers to how easily a reader can understand a written text. Several factors affect the readability level, such as the complexity of the text, its subject matter, and the reader{'}s background knowledge. Generating summaries based on different readability levels is critical for enabling knowledge consumption by diverse audiences. However, current text generation approaches lack refined control, resulting in texts that are not customized to readers{'} proficiency levels. In this work, we bridge this gap and study techniques to generate summaries at specified readability levels. Unlike previous methods that focus on a specific readability level (e.g., lay summarization), we generate summaries with fine-grained control over their readability. We develop three text generation techniques for controlling readability: (1) instruction-based readability control, (2) reinforcement learning to minimize the gap between requested and observed readability and (3) a decoding approach that uses lookahead to estimate the readability of upcoming decoding steps. We show that our generation methods significantly improve readability control on news summarization (CNN/DM dataset), as measured by various readability metrics and human judgement, establishing strong baselines for controllable readability in summarization.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ribeiro-etal-2023-generating">
<titleInfo>
<title>Generating Summaries with Controllable Readability Levels</title>
</titleInfo>
<name type="personal">
<namePart type="given">Leonardo</namePart>
<namePart type="given">F</namePart>
<namePart type="given">R</namePart>
<namePart type="family">Ribeiro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Markus</namePart>
<namePart type="family">Dreyer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Readability refers to how easily a reader can understand a written text. Several factors affect the readability level, such as the complexity of the text, its subject matter, and the reader’s background knowledge. Generating summaries based on different readability levels is critical for enabling knowledge consumption by diverse audiences. However, current text generation approaches lack refined control, resulting in texts that are not customized to readers’ proficiency levels. In this work, we bridge this gap and study techniques to generate summaries at specified readability levels. Unlike previous methods that focus on a specific readability level (e.g., lay summarization), we generate summaries with fine-grained control over their readability. We develop three text generation techniques for controlling readability: (1) instruction-based readability control, (2) reinforcement learning to minimize the gap between requested and observed readability and (3) a decoding approach that uses lookahead to estimate the readability of upcoming decoding steps. We show that our generation methods significantly improve readability control on news summarization (CNN/DM dataset), as measured by various readability metrics and human judgement, establishing strong baselines for controllable readability in summarization.</abstract>
<identifier type="citekey">ribeiro-etal-2023-generating</identifier>
<identifier type="doi">10.18653/v1/2023.emnlp-main.714</identifier>
<location>
<url>https://aclanthology.org/2023.emnlp-main.714</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>11669</start>
<end>11687</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Generating Summaries with Controllable Readability Levels
%A Ribeiro, Leonardo F. R.
%A Bansal, Mohit
%A Dreyer, Markus
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F ribeiro-etal-2023-generating
%X Readability refers to how easily a reader can understand a written text. Several factors affect the readability level, such as the complexity of the text, its subject matter, and the reader’s background knowledge. Generating summaries based on different readability levels is critical for enabling knowledge consumption by diverse audiences. However, current text generation approaches lack refined control, resulting in texts that are not customized to readers’ proficiency levels. In this work, we bridge this gap and study techniques to generate summaries at specified readability levels. Unlike previous methods that focus on a specific readability level (e.g., lay summarization), we generate summaries with fine-grained control over their readability. We develop three text generation techniques for controlling readability: (1) instruction-based readability control, (2) reinforcement learning to minimize the gap between requested and observed readability and (3) a decoding approach that uses lookahead to estimate the readability of upcoming decoding steps. We show that our generation methods significantly improve readability control on news summarization (CNN/DM dataset), as measured by various readability metrics and human judgement, establishing strong baselines for controllable readability in summarization.
%R 10.18653/v1/2023.emnlp-main.714
%U https://aclanthology.org/2023.emnlp-main.714
%U https://doi.org/10.18653/v1/2023.emnlp-main.714
%P 11669-11687
Markdown (Informal)
[Generating Summaries with Controllable Readability Levels](https://aclanthology.org/2023.emnlp-main.714) (Ribeiro et al., EMNLP 2023)
ACL
- Leonardo F. R. Ribeiro, Mohit Bansal, and Markus Dreyer. 2023. Generating Summaries with Controllable Readability Levels. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 11669–11687, Singapore. Association for Computational Linguistics.