@inproceedings{c-lara-instance-etal-2023-using,
title = "Using {C}-{LARA} to evaluate {GPT}-4{'}s multilingual processing",
author = "C-LARA-Instance, ChatGPT and
Chiera, Belinda and
Chua, Cathy and
Raheb, Chadi and
Rayner, Manny and
Simonsen, Annika and
Xiang, Zhengkang and
Zviel-Girshin, Rina",
editor = "Muresan, Smaranda and
Chen, Vivian and
Casey, Kennington and
David, Vandyke and
Nina, Dethlefs and
Koji, Inoue and
Erik, Ekstedt and
Stefan, Ultes",
booktitle = "Proceedings of the 21st Annual Workshop of the Australasian Language Technology Association",
month = nov,
year = "2023",
address = "Melbourne, Australia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.alta-1.3",
pages = "20--29",
abstract = "We present a cross-linguistic study in which the open source C-LARA platform was used to evaluate GPT-4{'}s ability to perform several key tasks relevant to Computer Assisted Language Learning. For each of the languages English, Farsi, Faroese, Mandarin and Russian, we instructed GPT-4, through C-LARA, to write six different texts, using prompts chosen to obtain texts of widely differing character. We then further instructed GPT-4 to annotate each text with segmentation markup, glosses and lemma/part-of-speech information; native speakers hand-corrected the texts and annotations to obtain error rates on the different component tasks. The C-LARA platform makes it easy to combine the results into a single multimodal document, further facilitating checking of their correctness. GPT-4{'}s performance varied widely across languages and processing tasks, but performance on different text genres was roughly comparable. In some cases, most notably glossing of English text, we found that GPT-4 was consistently able to revise its annotations to improve them.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="c-lara-instance-etal-2023-using">
<titleInfo>
<title>Using C-LARA to evaluate GPT-4’s multilingual processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">ChatGPT</namePart>
<namePart type="family">C-LARA-Instance</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Belinda</namePart>
<namePart type="family">Chiera</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cathy</namePart>
<namePart type="family">Chua</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chadi</namePart>
<namePart type="family">Raheb</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manny</namePart>
<namePart type="family">Rayner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Annika</namePart>
<namePart type="family">Simonsen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhengkang</namePart>
<namePart type="family">Xiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rina</namePart>
<namePart type="family">Zviel-Girshin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 21st Annual Workshop of the Australasian Language Technology Association</title>
</titleInfo>
<name type="personal">
<namePart type="given">Smaranda</namePart>
<namePart type="family">Muresan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivian</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kennington</namePart>
<namePart type="family">Casey</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vandyke</namePart>
<namePart type="family">David</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dethlefs</namePart>
<namePart type="family">Nina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Inoue</namePart>
<namePart type="family">Koji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekstedt</namePart>
<namePart type="family">Erik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ultes</namePart>
<namePart type="family">Stefan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Melbourne, Australia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present a cross-linguistic study in which the open source C-LARA platform was used to evaluate GPT-4’s ability to perform several key tasks relevant to Computer Assisted Language Learning. For each of the languages English, Farsi, Faroese, Mandarin and Russian, we instructed GPT-4, through C-LARA, to write six different texts, using prompts chosen to obtain texts of widely differing character. We then further instructed GPT-4 to annotate each text with segmentation markup, glosses and lemma/part-of-speech information; native speakers hand-corrected the texts and annotations to obtain error rates on the different component tasks. The C-LARA platform makes it easy to combine the results into a single multimodal document, further facilitating checking of their correctness. GPT-4’s performance varied widely across languages and processing tasks, but performance on different text genres was roughly comparable. In some cases, most notably glossing of English text, we found that GPT-4 was consistently able to revise its annotations to improve them.</abstract>
<identifier type="citekey">c-lara-instance-etal-2023-using</identifier>
<location>
<url>https://aclanthology.org/2023.alta-1.3</url>
</location>
<part>
<date>2023-11</date>
<extent unit="page">
<start>20</start>
<end>29</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Using C-LARA to evaluate GPT-4’s multilingual processing
%A C-LARA-Instance, ChatGPT
%A Chiera, Belinda
%A Chua, Cathy
%A Raheb, Chadi
%A Rayner, Manny
%A Simonsen, Annika
%A Xiang, Zhengkang
%A Zviel-Girshin, Rina
%Y Muresan, Smaranda
%Y Chen, Vivian
%Y Casey, Kennington
%Y David, Vandyke
%Y Nina, Dethlefs
%Y Koji, Inoue
%Y Erik, Ekstedt
%Y Stefan, Ultes
%S Proceedings of the 21st Annual Workshop of the Australasian Language Technology Association
%D 2023
%8 November
%I Association for Computational Linguistics
%C Melbourne, Australia
%F c-lara-instance-etal-2023-using
%X We present a cross-linguistic study in which the open source C-LARA platform was used to evaluate GPT-4’s ability to perform several key tasks relevant to Computer Assisted Language Learning. For each of the languages English, Farsi, Faroese, Mandarin and Russian, we instructed GPT-4, through C-LARA, to write six different texts, using prompts chosen to obtain texts of widely differing character. We then further instructed GPT-4 to annotate each text with segmentation markup, glosses and lemma/part-of-speech information; native speakers hand-corrected the texts and annotations to obtain error rates on the different component tasks. The C-LARA platform makes it easy to combine the results into a single multimodal document, further facilitating checking of their correctness. GPT-4’s performance varied widely across languages and processing tasks, but performance on different text genres was roughly comparable. In some cases, most notably glossing of English text, we found that GPT-4 was consistently able to revise its annotations to improve them.
%U https://aclanthology.org/2023.alta-1.3
%P 20-29
Markdown (Informal)
[Using C-LARA to evaluate GPT-4’s multilingual processing](https://aclanthology.org/2023.alta-1.3) (C-LARA-Instance et al., ALTA 2023)
ACL
- ChatGPT C-LARA-Instance, Belinda Chiera, Cathy Chua, Chadi Raheb, Manny Rayner, Annika Simonsen, Zhengkang Xiang, and Rina Zviel-Girshin. 2023. Using C-LARA to evaluate GPT-4’s multilingual processing. In Proceedings of the 21st Annual Workshop of the Australasian Language Technology Association, pages 20–29, Melbourne, Australia. Association for Computational Linguistics.