TAMU at KBP 2017: Event Nugget Detection and Coreference Resolution

TL;DR

This paper presents TAMU's system for event nugget detection and coreference resolution in TAC KBP 2017, utilizing syntactic features and joint modeling to improve performance in identifying event spans, types, realis status, and coreference links.

Contribution

The system leverages syntactic distribution of modifiers and joint modeling of detection and realis status, achieving competitive F1 scores with minimal features.

Findings

Modifiers have unique syntactic distributions useful for detection.

Joint modeling improves detection and classification performance.

Achieved F1 scores of 57.72, 44.27, 42.47 for detection, type, and realis tasks.

Abstract

In this paper, we describe TAMU's system submitted to the TAC KBP 2017 event nugget detection and coreference resolution task. Our system builds on the statistical and empirical observations made on training and development data. We found that modifiers of event nuggets tend to have unique syntactic distribution. Their parts-of-speech tags and dependency relations provides them essential characteristics that are useful in identifying their span and also defining their types and realis status. We further found that the joint modeling of event span detection and realis status identification performs better than the individual models for both tasks. Our simple system designed using minimal features achieved the micro-average F1 scores of 57.72, 44.27 and 42.47 for event span detection, type identification and realis status classification tasks respectively. Also, our system achieved the CoNLL F1 score of 27.20 in event coreference resolution task.