Knowledge-Based News Event Analysis Toolkit Oktie Hassanzadeh hassanzadeh@us.ibm.com 0 Parul Awasthy awasthyp@us.ibm.com 0 Ken Barker kjbarker@us.ibm.com 0 Onkar Bhardwaj onkarbhardwaj@ibm.com 0 Debarun Bhattacharjya debarunb@us.ibm.com 0 Mark Feblowitz 0 Aamod Khatiwada khatiwada.a@northeastern.edu 0 1 Lee Martie Lee.Martie@ibm.com 0 Steve Fonin Mbouadeu steve.mbouadeu19@my.stjohns.edu 0 3 Jian Ni 0 Anik Saha sahaa@rpi.edu 0 2 Sola Shirai 0 2 Kavitha Srinivas kavitha.srinivas@ibm.com 0 Lucy Yip Lucy.Yip@ibm.com 0 IBM Research , Yorktown Heights, NY , USA Khoury College of Computer Sciences, Northeastern University , Boston, MA , USA Rensselaer Polytechnic Institute , Troy, NY , United States St. John's University , NY , USA

We present an overview of our knowledge-based news event analysis toolkit. The toolkit is powered by a knowledge graph (KG) of event-related concepts and relations curated from Wikidata and enriched through knowledge extraction from text as well as a variety of link prediction methods. We describe each of the functions the toolkit provides and an overview of its various components. We present use cases in enterprise risk management, scenario planning, and media intelligence. We also discuss a number of lessons learned and directions for future research.

 Third-Party News Providers Event Identification Neural Concept Linking Zero-Shot Text Classifier Neural Question Answering Models

Knowledge Graph of Events & Consequences … e1 e2 …

… … Examples

 Causal Knowledge Extraction Pattern Matching + Neural NLI Models Neural Relation Extraction Models Event Sequences Analysis Event Sequence Models Event Sequence Extraction Event Analysis & Forecasting APIs News Retrieval Event Identification Causal Analysis & Forecasting Causal Knowledge Extraction Profile

can augment the included knowledge base or curate a custom knowledge base for their domain of interest. Figure 1 presents the current architecture of our toolkit [ 1 ]. We outline several challenges we faced in applying state-of-the-art concept linking, knowledge extraction, and link prediction techniques to build our toolkit, provide a summary of lessons learned, and present a number of research challenges that need to be addressed. In particular: • We outline the use of Wikidata as a primary source of knowledge, report on the challenges we faced with respect to the current coverage of event-related concepts in Wikidata, and how the existing knowledge in Wikidata can be enriched through automated knowledge extraction over Wikipedia articles. Our primary focus has been on weakly supervised and supervised neural models for causal relation extraction. • We describe our solution for mapping news headlines to concepts in our KG, and report on challenges in applying existing concept linking methods to this problem. • We report on the performance of several rule-based and knowledge graph embeddings based approaches for link prediction to enrich our KG. We also report on the challenges we faced in applying existing techniques for reasoning about potential consequences of a new event as a novel mechanism for event forecasting. • We also report on our preliminary results on automatically extracting structured event sequences from textual corpora and applying event sequence models as a mechanism of learning complex relations between event types in our KG.

[1] O. Hassanzadeh , P. Awasthy , K. Barker , O. Bhardwaj , D. Bhattacharjya , M. Feblowitz , L. Martie , J. Ni , K. Srinivas , L. Yip , Knowledge-based news event analysis & forecasting toolkit , in: IJCAI (Demonstration Track) , 2022 .