Placing (Historical) Facts on a Timeline: A Classification cum Coref Resolution Approach

TL;DR

This paper presents a two-stage system that combines generative adversarial learning and knowledge-based tags to classify important sentences and resolve event coreferences, enabling effective timeline generation from historical texts.

Contribution

It introduces a novel two-stage approach integrating GANs and knowledge tags for event classification and coreference resolution in historical document analysis.

Findings

Effective timeline generation demonstrated on two historical texts

Improved event coreference resolution accuracy

Potential to assist historians in research and socio-political analysis

Abstract

A timeline provides one of the most effective ways to visualize the important historical facts that occurred over a period of time, presenting the insights that may not be so apparent from reading the equivalent information in textual form. By leveraging generative adversarial learning for important sentence classification and by assimilating knowledge based tags for improving the performance of event coreference resolution we introduce a two staged system for event timeline generation from multiple (historical) text documents. We demonstrate our results on two manually annotated historical text documents. Our results can be extremely helpful for historians, in advancing research in history and in understanding the socio-political landscape of a country as reflected in the writings of famous personas.