@inproceedings{nebhi-szaszak-2023-automatic,
title = "Automatic Assessment Of Spoken {E}nglish Proficiency Based on Multimodal and Multitask Transformers",
author = {Nebhi, Kamel and
Szasz{\'a}k, Gy{\"o}rgy},
editor = "Mitkov, Ruslan and
Angelova, Galia",
booktitle = "Proceedings of the 14th International Conference on Recent Advances in Natural Language Processing",
month = sep,
year = "2023",
address = "Varna, Bulgaria",
publisher = "INCOMA Ltd., Shoumen, Bulgaria",
url = "https://aclanthology.org/2023.ranlp-1.83",
pages = "769--776",
abstract = "This paper describes technology developed to automatically grade students on their English spontaneous spoken language proficiency with common european framework of reference for languages (CEFR) level. Our automated assessment system contains two tasks: elicited imitation and spontaneous speech assessment. Spontaneous speech assessment is a challenging task that requires evaluating various aspects of speech quality, content, and coherence. In this paper, we propose a multimodal and multitask transformer model that leverages both audio and text features to perform three tasks: scoring, coherence modeling, and prompt relevancy scoring. Our model uses a fusion of multiple features and multiple modality attention to capture the interactions between audio and text modalities and learn from different sources of information.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nebhi-szaszak-2023-automatic">
<titleInfo>
<title>Automatic Assessment Of Spoken English Proficiency Based on Multimodal and Multitask Transformers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kamel</namePart>
<namePart type="family">Nebhi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">György</namePart>
<namePart type="family">Szaszák</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 14th International Conference on Recent Advances in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ruslan</namePart>
<namePart type="family">Mitkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Galia</namePart>
<namePart type="family">Angelova</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>This paper describes technology developed to automatically grade students on their English spontaneous spoken language proficiency with common european framework of reference for languages (CEFR) level. Our automated assessment system contains two tasks: elicited imitation and spontaneous speech assessment. Spontaneous speech assessment is a challenging task that requires evaluating various aspects of speech quality, content, and coherence. In this paper, we propose a multimodal and multitask transformer model that leverages both audio and text features to perform three tasks: scoring, coherence modeling, and prompt relevancy scoring. Our model uses a fusion of multiple features and multiple modality attention to capture the interactions between audio and text modalities and learn from different sources of information.</abstract>
<identifier type="citekey">nebhi-szaszak-2023-automatic</identifier>
<location>
<url>https://aclanthology.org/2023.ranlp-1.83</url>
</location>
<part>
<date>2023-09</date>
<extent unit="page">
<start>769</start>
<end>776</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Automatic Assessment Of Spoken English Proficiency Based on Multimodal and Multitask Transformers
%A Nebhi, Kamel
%A Szaszák, György
%Y Mitkov, Ruslan
%Y Angelova, Galia
%S Proceedings of the 14th International Conference on Recent Advances in Natural Language Processing
%D 2023
%8 September
%I INCOMA Ltd., Shoumen, Bulgaria
%C Varna, Bulgaria
%F nebhi-szaszak-2023-automatic
%X This paper describes technology developed to automatically grade students on their English spontaneous spoken language proficiency with common european framework of reference for languages (CEFR) level. Our automated assessment system contains two tasks: elicited imitation and spontaneous speech assessment. Spontaneous speech assessment is a challenging task that requires evaluating various aspects of speech quality, content, and coherence. In this paper, we propose a multimodal and multitask transformer model that leverages both audio and text features to perform three tasks: scoring, coherence modeling, and prompt relevancy scoring. Our model uses a fusion of multiple features and multiple modality attention to capture the interactions between audio and text modalities and learn from different sources of information.
%U https://aclanthology.org/2023.ranlp-1.83
%P 769-776
Markdown (Informal)
[Automatic Assessment Of Spoken English Proficiency Based on Multimodal and Multitask Transformers](https://aclanthology.org/2023.ranlp-1.83) (Nebhi & Szaszák, RANLP 2023)
ACL