@inproceedings{sawhney-etal-2021-multimodal,
title = "Multimodal Multi-Speaker Merger {\&} Acquisition Financial Modeling: A New Task, Dataset, and Neural Baselines",
author = "Sawhney, Ramit and
Goyal, Mihir and
Goel, Prakhar and
Mathur, Puneet and
Shah, Rajiv Ratn",
editor = "Zong, Chengqing and
Xia, Fei and
Li, Wenjie and
Navigli, Roberto",
booktitle = "Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.acl-long.526",
doi = "10.18653/v1/2021.acl-long.526",
pages = "6751--6762",
abstract = "Risk prediction is an essential task in financial markets. Merger and Acquisition (M{\&}A) calls provide key insights into the claims made by company executives about the restructuring of the financial firms. Extracting vocal and textual cues from M{\&}A calls can help model the risk associated with such financial activities. To aid the analysis of M{\&}A calls, we curate a dataset of conference call transcripts and their corresponding audio recordings for the time period ranging from 2016 to 2020. We introduce M3ANet, a baseline architecture that takes advantage of the multimodal multi-speaker input to forecast the financial risk associated with the M{\&}A calls. Empirical results prove that the task is challenging, with the pro-posed architecture performing marginally better than strong BERT-based baselines. We release the M3A dataset and benchmark models to motivate future research on this challenging problem domain.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sawhney-etal-2021-multimodal">
<titleInfo>
<title>Multimodal Multi-Speaker Merger & Acquisition Financial Modeling: A New Task, Dataset, and Neural Baselines</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ramit</namePart>
<namePart type="family">Sawhney</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mihir</namePart>
<namePart type="family">Goyal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Prakhar</namePart>
<namePart type="family">Goel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Puneet</namePart>
<namePart type="family">Mathur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rajiv</namePart>
<namePart type="given">Ratn</namePart>
<namePart type="family">Shah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fei</namePart>
<namePart type="family">Xia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenjie</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roberto</namePart>
<namePart type="family">Navigli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Risk prediction is an essential task in financial markets. Merger and Acquisition (M&A) calls provide key insights into the claims made by company executives about the restructuring of the financial firms. Extracting vocal and textual cues from M&A calls can help model the risk associated with such financial activities. To aid the analysis of M&A calls, we curate a dataset of conference call transcripts and their corresponding audio recordings for the time period ranging from 2016 to 2020. We introduce M3ANet, a baseline architecture that takes advantage of the multimodal multi-speaker input to forecast the financial risk associated with the M&A calls. Empirical results prove that the task is challenging, with the pro-posed architecture performing marginally better than strong BERT-based baselines. We release the M3A dataset and benchmark models to motivate future research on this challenging problem domain.</abstract>
<identifier type="citekey">sawhney-etal-2021-multimodal</identifier>
<identifier type="doi">10.18653/v1/2021.acl-long.526</identifier>
<location>
<url>https://aclanthology.org/2021.acl-long.526</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>6751</start>
<end>6762</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multimodal Multi-Speaker Merger & Acquisition Financial Modeling: A New Task, Dataset, and Neural Baselines
%A Sawhney, Ramit
%A Goyal, Mihir
%A Goel, Prakhar
%A Mathur, Puneet
%A Shah, Rajiv Ratn
%Y Zong, Chengqing
%Y Xia, Fei
%Y Li, Wenjie
%Y Navigli, Roberto
%S Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
%D 2021
%8 August
%I Association for Computational Linguistics
%C Online
%F sawhney-etal-2021-multimodal
%X Risk prediction is an essential task in financial markets. Merger and Acquisition (M&A) calls provide key insights into the claims made by company executives about the restructuring of the financial firms. Extracting vocal and textual cues from M&A calls can help model the risk associated with such financial activities. To aid the analysis of M&A calls, we curate a dataset of conference call transcripts and their corresponding audio recordings for the time period ranging from 2016 to 2020. We introduce M3ANet, a baseline architecture that takes advantage of the multimodal multi-speaker input to forecast the financial risk associated with the M&A calls. Empirical results prove that the task is challenging, with the pro-posed architecture performing marginally better than strong BERT-based baselines. We release the M3A dataset and benchmark models to motivate future research on this challenging problem domain.
%R 10.18653/v1/2021.acl-long.526
%U https://aclanthology.org/2021.acl-long.526
%U https://doi.org/10.18653/v1/2021.acl-long.526
%P 6751-6762
Markdown (Informal)
[Multimodal Multi-Speaker Merger & Acquisition Financial Modeling: A New Task, Dataset, and Neural Baselines](https://aclanthology.org/2021.acl-long.526) (Sawhney et al., ACL-IJCNLP 2021)
ACL