@inproceedings{tack-etal-2023-bea,
title = "The {BEA} 2023 Shared Task on Generating {AI} Teacher Responses in Educational Dialogues",
author = {Tack, Ana{\"\i}s and
Kochmar, Ekaterina and
Yuan, Zheng and
Bibauw, Serge and
Piech, Chris},
editor = {Kochmar, Ekaterina and
Burstein, Jill and
Horbach, Andrea and
Laarmann-Quante, Ronja and
Madnani, Nitin and
Tack, Ana{\"\i}s and
Yaneva, Victoria and
Yuan, Zheng and
Zesch, Torsten},
booktitle = "Proceedings of the 18th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2023)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.bea-1.64",
doi = "10.18653/v1/2023.bea-1.64",
pages = "785--795",
abstract = "This paper describes the results of the first shared task on generation of teacher responses in educational dialogues. The goal of the task was to benchmark the ability of generative language models to act as AI teachers, replying to a student in a teacher-student dialogue. Eight teams participated in the competition hosted on CodaLab and experimented with a wide variety of state-of-the-art models, including Alpaca, Bloom, DialoGPT, DistilGPT-2, Flan-T5, GPT- 2, GPT-3, GPT-4, LLaMA, OPT-2.7B, and T5- base. Their submissions were automatically scored using BERTScore and DialogRPT metrics, and the top three among them were further manually evaluated in terms of pedagogical ability based on Tack and Piech (2022). The NAISTeacher system, which ranked first in both automated and human evaluation, generated responses with GPT-3.5 Turbo using an ensemble of prompts and DialogRPT-based ranking of responses for given dialogue contexts. Despite promising achievements of the participating teams, the results also highlight the need for evaluation metrics better suited to educational contexts.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tack-etal-2023-bea">
<titleInfo>
<title>The BEA 2023 Shared Task on Generating AI Teacher Responses in Educational Dialogues</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anaïs</namePart>
<namePart type="family">Tack</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Kochmar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zheng</namePart>
<namePart type="family">Yuan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Serge</namePart>
<namePart type="family">Bibauw</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chris</namePart>
<namePart type="family">Piech</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 18th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2023)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Kochmar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jill</namePart>
<namePart type="family">Burstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrea</namePart>
<namePart type="family">Horbach</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ronja</namePart>
<namePart type="family">Laarmann-Quante</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nitin</namePart>
<namePart type="family">Madnani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anaïs</namePart>
<namePart type="family">Tack</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Victoria</namePart>
<namePart type="family">Yaneva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zheng</namePart>
<namePart type="family">Yuan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Torsten</namePart>
<namePart type="family">Zesch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes the results of the first shared task on generation of teacher responses in educational dialogues. The goal of the task was to benchmark the ability of generative language models to act as AI teachers, replying to a student in a teacher-student dialogue. Eight teams participated in the competition hosted on CodaLab and experimented with a wide variety of state-of-the-art models, including Alpaca, Bloom, DialoGPT, DistilGPT-2, Flan-T5, GPT- 2, GPT-3, GPT-4, LLaMA, OPT-2.7B, and T5- base. Their submissions were automatically scored using BERTScore and DialogRPT metrics, and the top three among them were further manually evaluated in terms of pedagogical ability based on Tack and Piech (2022). The NAISTeacher system, which ranked first in both automated and human evaluation, generated responses with GPT-3.5 Turbo using an ensemble of prompts and DialogRPT-based ranking of responses for given dialogue contexts. Despite promising achievements of the participating teams, the results also highlight the need for evaluation metrics better suited to educational contexts.</abstract>
<identifier type="citekey">tack-etal-2023-bea</identifier>
<identifier type="doi">10.18653/v1/2023.bea-1.64</identifier>
<location>
<url>https://aclanthology.org/2023.bea-1.64</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>785</start>
<end>795</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The BEA 2023 Shared Task on Generating AI Teacher Responses in Educational Dialogues
%A Tack, Anaïs
%A Kochmar, Ekaterina
%A Yuan, Zheng
%A Bibauw, Serge
%A Piech, Chris
%Y Kochmar, Ekaterina
%Y Burstein, Jill
%Y Horbach, Andrea
%Y Laarmann-Quante, Ronja
%Y Madnani, Nitin
%Y Tack, Anaïs
%Y Yaneva, Victoria
%Y Yuan, Zheng
%Y Zesch, Torsten
%S Proceedings of the 18th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2023)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F tack-etal-2023-bea
%X This paper describes the results of the first shared task on generation of teacher responses in educational dialogues. The goal of the task was to benchmark the ability of generative language models to act as AI teachers, replying to a student in a teacher-student dialogue. Eight teams participated in the competition hosted on CodaLab and experimented with a wide variety of state-of-the-art models, including Alpaca, Bloom, DialoGPT, DistilGPT-2, Flan-T5, GPT- 2, GPT-3, GPT-4, LLaMA, OPT-2.7B, and T5- base. Their submissions were automatically scored using BERTScore and DialogRPT metrics, and the top three among them were further manually evaluated in terms of pedagogical ability based on Tack and Piech (2022). The NAISTeacher system, which ranked first in both automated and human evaluation, generated responses with GPT-3.5 Turbo using an ensemble of prompts and DialogRPT-based ranking of responses for given dialogue contexts. Despite promising achievements of the participating teams, the results also highlight the need for evaluation metrics better suited to educational contexts.
%R 10.18653/v1/2023.bea-1.64
%U https://aclanthology.org/2023.bea-1.64
%U https://doi.org/10.18653/v1/2023.bea-1.64
%P 785-795
Markdown (Informal)
[The BEA 2023 Shared Task on Generating AI Teacher Responses in Educational Dialogues](https://aclanthology.org/2023.bea-1.64) (Tack et al., BEA 2023)
ACL