@inproceedings{yaari-etal-2022-aligned,
title = "The Aligned Multimodal Movie Treebank: An audio, video, dependency-parse treebank",
author = "Yaari, Adam and
DeWitt, Jan and
Hu, Henry and
Stankovits, Bennett and
Felshin, Sue and
Berzak, Yevgeni and
Aparicio, Helena and
Katz, Boris and
Cases, Ignacio and
Barbu, Andrei",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.emnlp-main.648",
doi = "10.18653/v1/2022.emnlp-main.648",
pages = "9531--9539",
abstract = "Treebanks have traditionally included only text and were derived from written sources such as newspapers or the web. We introduce the Aligned Multimodal Movie Treebank (AMMT), an English language treebank derived from dialog in Hollywood movies which includes transcriptions of the audio-visual streams with word-level alignment, as well as part of speech tags and dependency parses in the Universal Dependencies formalism. AMMT consists of 31,264 sentences and 218,090 words, that will amount to the 3rd largest UD English treebank and the only multimodal treebank in UD. To help with the web-based annotation effort, we also introduce the Efficient Audio Alignment Annotator (EAAA), a companion tool that enables annotators to significantly speed-up their annotation processes.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yaari-etal-2022-aligned">
<titleInfo>
<title>The Aligned Multimodal Movie Treebank: An audio, video, dependency-parse treebank</title>
</titleInfo>
<name type="personal">
<namePart type="given">Adam</namePart>
<namePart type="family">Yaari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">DeWitt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henry</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bennett</namePart>
<namePart type="family">Stankovits</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sue</namePart>
<namePart type="family">Felshin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yevgeni</namePart>
<namePart type="family">Berzak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helena</namePart>
<namePart type="family">Aparicio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Boris</namePart>
<namePart type="family">Katz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ignacio</namePart>
<namePart type="family">Cases</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrei</namePart>
<namePart type="family">Barbu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yoav</namePart>
<namePart type="family">Goldberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zornitsa</namePart>
<namePart type="family">Kozareva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Treebanks have traditionally included only text and were derived from written sources such as newspapers or the web. We introduce the Aligned Multimodal Movie Treebank (AMMT), an English language treebank derived from dialog in Hollywood movies which includes transcriptions of the audio-visual streams with word-level alignment, as well as part of speech tags and dependency parses in the Universal Dependencies formalism. AMMT consists of 31,264 sentences and 218,090 words, that will amount to the 3rd largest UD English treebank and the only multimodal treebank in UD. To help with the web-based annotation effort, we also introduce the Efficient Audio Alignment Annotator (EAAA), a companion tool that enables annotators to significantly speed-up their annotation processes.</abstract>
<identifier type="citekey">yaari-etal-2022-aligned</identifier>
<identifier type="doi">10.18653/v1/2022.emnlp-main.648</identifier>
<location>
<url>https://aclanthology.org/2022.emnlp-main.648</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>9531</start>
<end>9539</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The Aligned Multimodal Movie Treebank: An audio, video, dependency-parse treebank
%A Yaari, Adam
%A DeWitt, Jan
%A Hu, Henry
%A Stankovits, Bennett
%A Felshin, Sue
%A Berzak, Yevgeni
%A Aparicio, Helena
%A Katz, Boris
%A Cases, Ignacio
%A Barbu, Andrei
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F yaari-etal-2022-aligned
%X Treebanks have traditionally included only text and were derived from written sources such as newspapers or the web. We introduce the Aligned Multimodal Movie Treebank (AMMT), an English language treebank derived from dialog in Hollywood movies which includes transcriptions of the audio-visual streams with word-level alignment, as well as part of speech tags and dependency parses in the Universal Dependencies formalism. AMMT consists of 31,264 sentences and 218,090 words, that will amount to the 3rd largest UD English treebank and the only multimodal treebank in UD. To help with the web-based annotation effort, we also introduce the Efficient Audio Alignment Annotator (EAAA), a companion tool that enables annotators to significantly speed-up their annotation processes.
%R 10.18653/v1/2022.emnlp-main.648
%U https://aclanthology.org/2022.emnlp-main.648
%U https://doi.org/10.18653/v1/2022.emnlp-main.648
%P 9531-9539
Markdown (Informal)
[The Aligned Multimodal Movie Treebank: An audio, video, dependency-parse treebank](https://aclanthology.org/2022.emnlp-main.648) (Yaari et al., EMNLP 2022)
ACL
- Adam Yaari, Jan DeWitt, Henry Hu, Bennett Stankovits, Sue Felshin, Yevgeni Berzak, Helena Aparicio, Boris Katz, Ignacio Cases, and Andrei Barbu. 2022. The Aligned Multimodal Movie Treebank: An audio, video, dependency-parse treebank. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 9531–9539, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.