|TREND||DATASET||BEST METHOD||PAPER TITLE||PAPER||CODE||COMPARE|
Event extraction from news articles is a commonly required prerequisite for various tasks, such as article summarization, article clustering, and news aggregation.
We examine the capabilities of a unified, multi-task framework for three information extraction tasks: named entity recognition, relation extraction, and event extraction.
Ranked #1 on Relation Extraction on ACE 2005 (Sentence Encoder metric, using extra training data)
Hate speech detection on Twitter is critical for applications like controversial event extraction, building AI chatterbots, content recommendation, and sentiment analysis.
Event extraction is of practical utility in natural language processing.
Most existing event extraction (EE) methods merely extract event arguments within the sentence scope.
We propose a novel neural network model for joint part-of-speech (POS) tagging and dependency parsing.
Ranked #13 on Dependency Parsing on Penn Treebank
Events and entities are closely related; entities are often actors or participants in events and events without entities are uncommon.
We consider open domain event extraction, the task of extracting unconstraint types of events from news clusters.
Additionally, we include an approach to representing text annotations in which annotation subgraphs, or semantic summaries, are used to show relationships outside of the sequential context of the text itself.