Multimodal Multi-Speaker Merger & Acquisition Financial Modeling: A New Task, Dataset, and Neural Baselines

Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, pages 6751–6762 August 1–6, 2021. ©2021 Association for Computational Linguistics 6751 Multimodal Multi-Speaker Merger & Acquisition Financial Modeling: A New Task, Dataset, and Neural Baselines Ramit Sawhney†∗, Mihir Goyal†∗, Prakhar Goel†∗, Puneet Mathur‡, Rajiv Ratn Shah† † Department of Computer Engineering, IIIT Delhi ‡ University of Maryland, College Park {ramits, mihir17166, prakhar17306, rajivratn}@iiitd.ac.in ‡puneetm@umd.edu Abstract Risk prediction is an essential task in finan- cial 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 activi- ties. 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 asso- ciated with the M&A calls. Empirical results prove that the task is challenging, with the pro- posed architecture performing marginally bet- ter than strong BERT-based baselines. We re- lease the M3A dataset and benchmark models to motivate future research on this challenging problem domain. 1 Introduction Mergers and Acquisitions (M&As)1 conference calls are events preceding financial transactions involving two or more entities such that either one of the participant companies takes over the other(s) and establishes itself as the owner (termed as ”acquisition”) or when one company combines with another to become a joint entity (termed as ”merger”). In these M&A conference calls, the participating companies’ management makes a pre- sentation to the call participants, such as market analysts, media personnel, and other stakeholders, explaining the rationale for the deal and possible roadblocks to deal completion (Dasgupta et al., 2020). Following the presentation segment, there is a Q&A segment in which the call participants ask questions to which the management responds. ∗ Equal contribution 1https://www.investopedia.com/mergers-and-acquisitions Figure 1: A schematic of our proposed approach (M3A) that leverages three types of input modalities: text utter- ances from the call transcripts, audio clips, and speaker specific input, for financial modeling tasks. Building on the important information that M&As provide, academic research, the financial press, and other media give a great deal of atten- tion. One of these discussions’ principal aspects lies in how the deals may affect the company’s valuation (Moeller et al., 2003; Fraunhoffer et al., 2018) and future growth. A significant focus in financial and economic literature has been on un- derstanding whether M&As create or destroy value. Consequently, shareholders critically analyze the deals to estimate the potential stock price and stock price volatility post the M&A conference call. Identifying the gap in natural language process- ing (NLP) literature on the lack of resources to study M&A conference calls with their text tran- scripts and audio recordings, we take the first step in …

Content truncated to 500 words