@inproceedings{al-shaibani-ahmad-2023-consonant,
title = "Consonant is all you need: a compact representation of {E}nglish text for efficient {NLP}",
author = "Al-shaibani, Maged and
Ahmad, Irfan",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-emnlp.775",
doi = "10.18653/v1/2023.findings-emnlp.775",
pages = "11578--11588",
abstract = "In natural language processing (NLP), the representation of text plays a crucial role in various tasks such as language modeling, sentiment analysis, and machine translation. The standard approach is to represent text in the same way as we, as humans, read and write. In this paper, we propose a novel approach to represent text with only consonants which presents a compact representation of English text that offers improved efficiency without sacrificing performance. We exploit the fact that consonants are more discriminative than vowels and by representing text using consonants, we can significantly reduce the overall memory and compute footprint required for storing and processing textual data. We present two alternative representations: {`}consonants-only{'}, where we completely remove the vowels from the text, and {`}masked-vowels{'}, where we mask all the vowels into one special symbol. To evaluate our approaches, we conducted experiments on various NLP tasks, including text classification, part-of-speech (POS) tagging, named-entity recognition (NER), and neural machine translation (NMT), in addition to language modeling. Our results demonstrate that the proposed consonant-based representation achieves comparable performance compared to the standard text representation while requiring significantly fewer computational resources. Furthermore, we show that our representation can be seamlessly integrated with existing NLP models and frameworks, providing a practical solution for efficient text processing. Last but not the least, we present a technique to retrieve the vowel information from our processed text representation keeping in mind the need to reproduce text in human readable form in some NLP applications.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="al-shaibani-ahmad-2023-consonant">
<titleInfo>
<title>Consonant is all you need: a compact representation of English text for efficient NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maged</namePart>
<namePart type="family">Al-shaibani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Irfan</namePart>
<namePart type="family">Ahmad</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>Findings of the Association for Computational Linguistics: EMNLP 2023</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>In natural language processing (NLP), the representation of text plays a crucial role in various tasks such as language modeling, sentiment analysis, and machine translation. The standard approach is to represent text in the same way as we, as humans, read and write. In this paper, we propose a novel approach to represent text with only consonants which presents a compact representation of English text that offers improved efficiency without sacrificing performance. We exploit the fact that consonants are more discriminative than vowels and by representing text using consonants, we can significantly reduce the overall memory and compute footprint required for storing and processing textual data. We present two alternative representations: ‘consonants-only’, where we completely remove the vowels from the text, and ‘masked-vowels’, where we mask all the vowels into one special symbol. To evaluate our approaches, we conducted experiments on various NLP tasks, including text classification, part-of-speech (POS) tagging, named-entity recognition (NER), and neural machine translation (NMT), in addition to language modeling. Our results demonstrate that the proposed consonant-based representation achieves comparable performance compared to the standard text representation while requiring significantly fewer computational resources. Furthermore, we show that our representation can be seamlessly integrated with existing NLP models and frameworks, providing a practical solution for efficient text processing. Last but not the least, we present a technique to retrieve the vowel information from our processed text representation keeping in mind the need to reproduce text in human readable form in some NLP applications.</abstract>
<identifier type="citekey">al-shaibani-ahmad-2023-consonant</identifier>
<identifier type="doi">10.18653/v1/2023.findings-emnlp.775</identifier>
<location>
<url>https://aclanthology.org/2023.findings-emnlp.775</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>11578</start>
<end>11588</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Consonant is all you need: a compact representation of English text for efficient NLP
%A Al-shaibani, Maged
%A Ahmad, Irfan
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Findings of the Association for Computational Linguistics: EMNLP 2023
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F al-shaibani-ahmad-2023-consonant
%X In natural language processing (NLP), the representation of text plays a crucial role in various tasks such as language modeling, sentiment analysis, and machine translation. The standard approach is to represent text in the same way as we, as humans, read and write. In this paper, we propose a novel approach to represent text with only consonants which presents a compact representation of English text that offers improved efficiency without sacrificing performance. We exploit the fact that consonants are more discriminative than vowels and by representing text using consonants, we can significantly reduce the overall memory and compute footprint required for storing and processing textual data. We present two alternative representations: ‘consonants-only’, where we completely remove the vowels from the text, and ‘masked-vowels’, where we mask all the vowels into one special symbol. To evaluate our approaches, we conducted experiments on various NLP tasks, including text classification, part-of-speech (POS) tagging, named-entity recognition (NER), and neural machine translation (NMT), in addition to language modeling. Our results demonstrate that the proposed consonant-based representation achieves comparable performance compared to the standard text representation while requiring significantly fewer computational resources. Furthermore, we show that our representation can be seamlessly integrated with existing NLP models and frameworks, providing a practical solution for efficient text processing. Last but not the least, we present a technique to retrieve the vowel information from our processed text representation keeping in mind the need to reproduce text in human readable form in some NLP applications.
%R 10.18653/v1/2023.findings-emnlp.775
%U https://aclanthology.org/2023.findings-emnlp.775
%U https://doi.org/10.18653/v1/2023.findings-emnlp.775
%P 11578-11588
Markdown (Informal)
[Consonant is all you need: a compact representation of English text for efficient NLP](https://aclanthology.org/2023.findings-emnlp.775) (Al-shaibani & Ahmad, Findings 2023)
ACL