@inproceedings{irving-schoene-2024-meant,
title = "{MEANT}: Multimodal Encoder for Antecedent Information",
author = "Irving, Benjamin and
Schoene, Annika",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.emnlp-main.488",
pages = "8579--8600",
abstract = "The stock market provides a rich well of information that can be split across modalities, making it an ideal candidate for multimodal evaluation. Multimodal data plays an increasingly important role in the development of machine learning and has shown to positively impact performance. But information can do more than exist across modes{---} it can exist across time. How should we attend to temporal data that consists of multiple information types? This work introduces (i) the MEANT model, a Multimodal Encoder for Antecedent information and (ii) a new dataset called TempStock, which consists of price, Tweets, and graphical data with over a million Tweets from all of the companies in the S{\&}P 500 Index. We find that MEANT improves performance on existing baselines by over 15{\%}, and that the textual information affects performance far more than the visual information on our time-dependent task from our ablation study. The code and dataset will be made available upon publication.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="irving-schoene-2024-meant">
<titleInfo>
<title>MEANT: Multimodal Encoder for Antecedent Information</title>
</titleInfo>
<name type="personal">
<namePart type="given">Benjamin</namePart>
<namePart type="family">Irving</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Annika</namePart>
<namePart type="family">Schoene</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaser</namePart>
<namePart type="family">Al-Onaizan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The stock market provides a rich well of information that can be split across modalities, making it an ideal candidate for multimodal evaluation. Multimodal data plays an increasingly important role in the development of machine learning and has shown to positively impact performance. But information can do more than exist across modes— it can exist across time. How should we attend to temporal data that consists of multiple information types? This work introduces (i) the MEANT model, a Multimodal Encoder for Antecedent information and (ii) a new dataset called TempStock, which consists of price, Tweets, and graphical data with over a million Tweets from all of the companies in the S&P 500 Index. We find that MEANT improves performance on existing baselines by over 15%, and that the textual information affects performance far more than the visual information on our time-dependent task from our ablation study. The code and dataset will be made available upon publication.</abstract>
<identifier type="citekey">irving-schoene-2024-meant</identifier>
<location>
<url>https://aclanthology.org/2024.emnlp-main.488</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>8579</start>
<end>8600</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MEANT: Multimodal Encoder for Antecedent Information
%A Irving, Benjamin
%A Schoene, Annika
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F irving-schoene-2024-meant
%X The stock market provides a rich well of information that can be split across modalities, making it an ideal candidate for multimodal evaluation. Multimodal data plays an increasingly important role in the development of machine learning and has shown to positively impact performance. But information can do more than exist across modes— it can exist across time. How should we attend to temporal data that consists of multiple information types? This work introduces (i) the MEANT model, a Multimodal Encoder for Antecedent information and (ii) a new dataset called TempStock, which consists of price, Tweets, and graphical data with over a million Tweets from all of the companies in the S&P 500 Index. We find that MEANT improves performance on existing baselines by over 15%, and that the textual information affects performance far more than the visual information on our time-dependent task from our ablation study. The code and dataset will be made available upon publication.
%U https://aclanthology.org/2024.emnlp-main.488
%P 8579-8600
Markdown (Informal)
[MEANT: Multimodal Encoder for Antecedent Information](https://aclanthology.org/2024.emnlp-main.488) (Irving & Schoene, EMNLP 2024)
ACL
- Benjamin Irving and Annika Schoene. 2024. MEANT: Multimodal Encoder for Antecedent Information. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 8579–8600, Miami, Florida, USA. Association for Computational Linguistics.