@inproceedings{hemanthage-etal-2023-simplemtod,
title = "{S}imple{MTOD}: A Simple Language Model for Multimodal Task-Oriented Dialogue with Symbolic Scene Representation",
author = "Hemanthage, Bhathiya and
Dondrup, Christian and
Bartie, Phil and
Lemon, Oliver",
editor = "Amblard, Maxime and
Breitholtz, Ellen",
booktitle = "Proceedings of the 15th International Conference on Computational Semantics",
month = jun,
year = "2023",
address = "Nancy, France",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.iwcs-1.31",
pages = "293--304",
abstract = "SimpleMTOD is a simple language model which recasts several sub-tasks in multimodal task-oriented dialogues as sequence prediction tasks. SimpleMTOD is built on a large-scale transformer-based auto-regressive architecture, which has already proven to be successful in uni-modal task-oriented dialogues, and effectively leverages transfer learning from pretrained GPT-2. In-order to capture the semantics of visual scenes, we introduce both local and de-localized tokens for objects within a scene. De-localized tokens represent the type of an object rather than the specific object itself and so possess a consistent meaning across the dataset. SimpleMTOD achieves a state-of-the-art BLEU score (0.327) in the Response Generation sub-task of the SIMMC 2.0 test-std dataset while performing on par in other multimodal sub-tasks: Disambiguation, Coreference Resolution, and Dialog State Tracking. This is despite taking a minimalist approach for extracting visual (and non-visual) informa- tion. In addition the model does not rely on task-specific architectural changes such as classification heads.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hemanthage-etal-2023-simplemtod">
<titleInfo>
<title>SimpleMTOD: A Simple Language Model for Multimodal Task-Oriented Dialogue with Symbolic Scene Representation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bhathiya</namePart>
<namePart type="family">Hemanthage</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christian</namePart>
<namePart type="family">Dondrup</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Phil</namePart>
<namePart type="family">Bartie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Oliver</namePart>
<namePart type="family">Lemon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 15th International Conference on Computational Semantics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maxime</namePart>
<namePart type="family">Amblard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ellen</namePart>
<namePart type="family">Breitholtz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Nancy, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>SimpleMTOD is a simple language model which recasts several sub-tasks in multimodal task-oriented dialogues as sequence prediction tasks. SimpleMTOD is built on a large-scale transformer-based auto-regressive architecture, which has already proven to be successful in uni-modal task-oriented dialogues, and effectively leverages transfer learning from pretrained GPT-2. In-order to capture the semantics of visual scenes, we introduce both local and de-localized tokens for objects within a scene. De-localized tokens represent the type of an object rather than the specific object itself and so possess a consistent meaning across the dataset. SimpleMTOD achieves a state-of-the-art BLEU score (0.327) in the Response Generation sub-task of the SIMMC 2.0 test-std dataset while performing on par in other multimodal sub-tasks: Disambiguation, Coreference Resolution, and Dialog State Tracking. This is despite taking a minimalist approach for extracting visual (and non-visual) informa- tion. In addition the model does not rely on task-specific architectural changes such as classification heads.</abstract>
<identifier type="citekey">hemanthage-etal-2023-simplemtod</identifier>
<location>
<url>https://aclanthology.org/2023.iwcs-1.31</url>
</location>
<part>
<date>2023-06</date>
<extent unit="page">
<start>293</start>
<end>304</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SimpleMTOD: A Simple Language Model for Multimodal Task-Oriented Dialogue with Symbolic Scene Representation
%A Hemanthage, Bhathiya
%A Dondrup, Christian
%A Bartie, Phil
%A Lemon, Oliver
%Y Amblard, Maxime
%Y Breitholtz, Ellen
%S Proceedings of the 15th International Conference on Computational Semantics
%D 2023
%8 June
%I Association for Computational Linguistics
%C Nancy, France
%F hemanthage-etal-2023-simplemtod
%X SimpleMTOD is a simple language model which recasts several sub-tasks in multimodal task-oriented dialogues as sequence prediction tasks. SimpleMTOD is built on a large-scale transformer-based auto-regressive architecture, which has already proven to be successful in uni-modal task-oriented dialogues, and effectively leverages transfer learning from pretrained GPT-2. In-order to capture the semantics of visual scenes, we introduce both local and de-localized tokens for objects within a scene. De-localized tokens represent the type of an object rather than the specific object itself and so possess a consistent meaning across the dataset. SimpleMTOD achieves a state-of-the-art BLEU score (0.327) in the Response Generation sub-task of the SIMMC 2.0 test-std dataset while performing on par in other multimodal sub-tasks: Disambiguation, Coreference Resolution, and Dialog State Tracking. This is despite taking a minimalist approach for extracting visual (and non-visual) informa- tion. In addition the model does not rely on task-specific architectural changes such as classification heads.
%U https://aclanthology.org/2023.iwcs-1.31
%P 293-304
Markdown (Informal)
[SimpleMTOD: A Simple Language Model for Multimodal Task-Oriented Dialogue with Symbolic Scene Representation](https://aclanthology.org/2023.iwcs-1.31) (Hemanthage et al., IWCS 2023)
ACL