Discourse as a Function of Event: Profiling Discourse Structure in News Articles around the Main Event

Abstract

Understanding discourse structures of news articles is vital to effectively contextualize the occurrence of a news event. To enable computational modeling of news structures, we apply an existing theory of functional discourse structure for news articles that revolves around the main event and create a human-annotated corpus of 802 documents spanning over four domains and three media sources. Next, we propose several documentlevel neural-network models to automatically construct news content structures. Finally, we demonstrate that incorporating system predicted news structures yields new state-of-theart performance for event coreference resolution. The news documents we annotated are openly available and the annotations are publicly released for future research 1 .

RESIN: A Dockerized Schema-Guided Cross-document Cross-lingual Cross-media Information Extraction and Event Tracking System

“…Coreference Resolution. Previous neural models for event coreference resolution use noncontextual (Nguyen et al, 2016;Choubey et al, 2020;Huang et al, 2019) or contextual word representations . We incorporate a wide range of symbolic features Sammons et al, 2015;Ng, 2016, 2017;Duncan et al, 2017), such as event attributes and types, into our event coreference resolution module using a contextdependent gate mechanism.…”

“…Event extraction and tracking technologies can help us understand real-world events described in the overwhelming amount of news data, and how they are inter-connected. These techniques have already been proven helpful in various application domains, including news analysis (Glavaš and Štajner, 2013;Glavaš et al, 2014;Choubey et al, 2020), aiding natural disaster relief efforts (Panem et al, 2014;Zhang et al, 2018;Medina Maza et al, 2020), financial analysis (Ding et al, 2014(Ding et al, , 2016Yang et al, 2018;Jacobs et al, 2018;Ein-Dor et al, 2019;Özbayoglu et al, 2020) and healthcare monitoring (Raghavan et al, 2012;Jagannatha and Yu, 2016;Klassen et al, 2016;Jeblee and Hirst, 2018).…”

Exploiting Document Structures and Cluster Consistencies for Event Coreference Resolution

“…Our work focuses on the within-document setting for ECR where input event mentions are expected to appear in the same input documents; however, we also note prior works on crossdocument ECR (Lee et al, 2012a;Adrian Bejan and Harabagiu, 2014;Choubey and Huang, 2017;Kenyon-Dean et al, 2018;Barhom et al, 2019;Cattan et al, 2020). As such, for within-document ECR, previous methods have applied feature-based models for pairwise classifiers (Ahn, 2006;Cybulska and Vossen, 2015;Peng et al, 2016), spectral graph clustering , information propagation (Liu et al, 2014), markov logic networks (Lu et al, 2016), joint modeling of ECR with event detection (Araki and Mitamura, 2015;Lu et al, 2016;Chen and Ng, 2016;Lu and Ng, 2017), and recent deep learning models (Nguyen et al, 2016;Choubey and Huang, 2018;Huang et al, 2019;Choubey et al, 2020). Compared to previous deep learning works for ECR, our model presents a novel representation learning framework based on document structures to explicitly encode important interactions between relevant objects, and representation regularization to exploit the cluster consistency between golden and predicted clusters for event mentions.…”

Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Demonstrations

“…Coreference Resolution. Previous neural models for event coreference resolution use noncontextual Choubey et al, 2020; or contextual word representations . We incorporate a wide range of symbolic features Sammons et al, 2015;Ng, 2016, 2017;Duncan et al, 2017), such as event attributes and types, into our event coreference resolution module using a contextdependent gate mechanism.…”

“…Event extraction and tracking technologies can help us understand real-world events described in the overwhelming amount of news data, and how they are inter-connected. These techniques have already been proven helpful in various application domains, including news analysis (Glavaš and Štajner, 2013;Glavaš et al, 2014;Choubey et al, 2020), aiding natural disaster relief efforts (Panem et al, 2014;Medina Maza et al, 2020), financial analysis (Ding et al, 2014(Ding et al, , 2016Jacobs et al, 2018;Ein-Dor et al, 2019;Özbayoglu et al, 2020) and healthcare monitoring (Raghavan et al, 2012;Jagannatha and Yu, 2016;Klassen et al, 2016;Jeblee and Hirst, 2018).…”