Event Coreference Resolution via a Multi-loss Neural Network without Using Argument Information
This addresses error propagation issues in NLP for event coreference resolution, though it is incremental as it builds on existing neural approaches without arguments.
The paper tackles event coreference resolution by proposing a multi-loss neural network that avoids using event argument information to reduce error propagation, achieving significant performance improvements over state-of-the-art methods.
Event coreference resolution(ECR) is an important task in Natural Language Processing (NLP) and nearly all the existing approaches to this task rely on event argument information. However, these methods tend to suffer from error propagation from the stage of event argument extraction. Besides, not every event mention contains all arguments of an event, and argument information may confuse the model that events have arguments to detect event coreference in real text. Furthermore, the context information of an event is useful to infer the coreference between events. Thus, in order to reduce the errors propagated from event argument extraction and use context information effectively, we propose a multi-loss neural network model that does not need any argument information to do the within-document event coreference resolution task and achieve a significant performance than the state-of-the-art methods.