Command Palette
Search for a command to run...
Discourse as a Function of Event: Profiling Discourse Structure in News Articles around the Main Event
{Prafulla Kumar Choubey Ruihong Huang Lu Wang Aaron Lee}
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 document-level neural-network models to automatically construct news content structures. Finally, we demonstrate that incorporating system predicted news structures yields new state-of-the-art performance for event coreference resolution. The news documents we annotated are openly available and the annotations are publicly released for future research.
Benchmarks
| Benchmark | Methodology | Metrics |
|---|---|---|
| text-classification-on-newsdiscourse | Feature-based (SVM) (Choubey et al., 2020) | macro F1: 38.3 |
| text-classification-on-newsdiscourse | CRF Fine-grained (Choubey et al., 2020) | macro F1: 52.9 |
| text-classification-on-newsdiscourse | Document LSTM + Document encoding (Choubey et al., 2020) | macro F1: 54.4 |
Build AI with AI
From idea to launch — accelerate your AI development with free AI co-coding, out-of-the-box environment and best price of GPUs.