@inproceedings{shurtz-etal-2024-effects,
title = "The Effects of Pretraining in Video-Guided Machine Translation",
author = "Shurtz, Ammon and
Sorenson, Lawry and
Richardson, Stephen D.",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.1380/",
pages = "15888--15898",
abstract = "We propose an approach that improves the performance of VMT (Video-guided Machine Translation) models, which integrate text and video modalities. We experiment with the MAD (Movie Audio Descriptions) dataset, a new dataset which contains transcribed audio descriptions of movies. We find that the MAD dataset is more lexically rich than the VATEX dataset (the current VMT baseline), and we experiment with MAD pretraining to improve performance on the VATEX dataset. We experiment with two different video encoder architectures: a Conformer (Convolution-augmented Transformer) and a Transformer. Additionally, we conduct experiments by masking the source sentences to assess the degree to which the performance of both architectures improves due to pretraining on additional video data. Finally, we conduct an analysis of the transfer learning potential of a video dataset and compare it to pretraining on a text-only dataset. Our findings demonstrate that pretraining with a lexically rich dataset leads to significant improvements in model performance when models use both text and video modalities."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shurtz-etal-2024-effects">
<titleInfo>
<title>The Effects of Pretraining in Video-Guided Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ammon</namePart>
<namePart type="family">Shurtz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lawry</namePart>
<namePart type="family">Sorenson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stephen</namePart>
<namePart type="given">D</namePart>
<namePart type="family">Richardson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We propose an approach that improves the performance of VMT (Video-guided Machine Translation) models, which integrate text and video modalities. We experiment with the MAD (Movie Audio Descriptions) dataset, a new dataset which contains transcribed audio descriptions of movies. We find that the MAD dataset is more lexically rich than the VATEX dataset (the current VMT baseline), and we experiment with MAD pretraining to improve performance on the VATEX dataset. We experiment with two different video encoder architectures: a Conformer (Convolution-augmented Transformer) and a Transformer. Additionally, we conduct experiments by masking the source sentences to assess the degree to which the performance of both architectures improves due to pretraining on additional video data. Finally, we conduct an analysis of the transfer learning potential of a video dataset and compare it to pretraining on a text-only dataset. Our findings demonstrate that pretraining with a lexically rich dataset leads to significant improvements in model performance when models use both text and video modalities.</abstract>
<identifier type="citekey">shurtz-etal-2024-effects</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.1380/</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>15888</start>
<end>15898</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The Effects of Pretraining in Video-Guided Machine Translation
%A Shurtz, Ammon
%A Sorenson, Lawry
%A Richardson, Stephen D.
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F shurtz-etal-2024-effects
%X We propose an approach that improves the performance of VMT (Video-guided Machine Translation) models, which integrate text and video modalities. We experiment with the MAD (Movie Audio Descriptions) dataset, a new dataset which contains transcribed audio descriptions of movies. We find that the MAD dataset is more lexically rich than the VATEX dataset (the current VMT baseline), and we experiment with MAD pretraining to improve performance on the VATEX dataset. We experiment with two different video encoder architectures: a Conformer (Convolution-augmented Transformer) and a Transformer. Additionally, we conduct experiments by masking the source sentences to assess the degree to which the performance of both architectures improves due to pretraining on additional video data. Finally, we conduct an analysis of the transfer learning potential of a video dataset and compare it to pretraining on a text-only dataset. Our findings demonstrate that pretraining with a lexically rich dataset leads to significant improvements in model performance when models use both text and video modalities.
%U https://aclanthology.org/2024.lrec-main.1380/
%P 15888-15898
Markdown (Informal)
[The Effects of Pretraining in Video-Guided Machine Translation](https://aclanthology.org/2024.lrec-main.1380/) (Shurtz et al., LREC-COLING 2024)
ACL
- Ammon Shurtz, Lawry Sorenson, and Stephen D. Richardson. 2024. The Effects of Pretraining in Video-Guided Machine Translation. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 15888–15898, Torino, Italia. ELRA and ICCL.