Modality and Negation in Event Extraction
This addresses the issue of inaccurate event extraction for downstream NLP tasks like Question Answering and Fact-checking, but it is incremental as it builds on existing lexicon-based methods.
The paper tackled the problem of NLP systems incorrectly extracting events that did not happen due to modality and negation in language, particularly in political news, and presented a lexicon-based event extraction system that shows sufficient strength for use in downstream applications.
Language provides speakers with a rich system of modality for expressing thoughts about events, without being committed to their actual occurrence. Modality is commonly used in the political news domain, where both actual and possible courses of events are discussed. NLP systems struggle with these semantic phenomena, often incorrectly extracting events which did not happen, which can lead to issues in downstream applications. We present an open-domain, lexicon-based event extraction system that captures various types of modality. This information is valuable for Question Answering, Knowledge Graph construction and Fact-checking tasks, and our evaluation shows that the system is sufficiently strong to be used in downstream applications.