Ensemble Detection of Single & Multiple Events at Sentence-Level
This work addresses event classification for NLP, IR, and personalization systems, but it is incremental as it builds on existing multi-label methods with modest improvements.
The paper tackled event classification at the sentence level by exploring new multi-label methods that capture relations between event types, improving average F1 by 2.8% over Binary Relevance, and reducing the problem to a more tractable imbalanced multiclass setup for a 4.6% gain.
Event classification at sentence level is an important Information Extraction task with applications in several NLP, IR, and personalization systems. Multi-label binary relevance (BR) are the state-of-art methods. In this work, we explored new multi-label methods known for capturing relations between event types. These new methods, such as the ensemble Chain of Classifiers, improve the F1 on average across the 6 labels by 2.8% over the Binary Relevance. The low occurrence of multi-label sentences motivated the reduction of the hard imbalanced multi-label classification problem with low number of occurrences of multiple labels per instance to an more tractable imbalanced multiclass problem with better results (+ 4.6%). We report the results of adding new features, such as sentiment strength, rhetorical signals, domain-id (source-id and date), and key-phrases in both single-label and multi-label event classification scenarios.