Boosting Information Extraction Systems with Character-level Neural Networks and Free Noisy Supervision

no code implementations • WS 2017 • Philipp Meerkamp, Zhengyi Zhou

We present an architecture to boost the precision of existing information extraction systems.

Structured Prediction Time Series Analysis

Information Extraction with Character-level Neural Networks and Free Noisy Supervision

no code implementations • 13 Dec 2016 • Philipp Meerkamp, Zhengyi Zhou

We present an architecture for information extraction from text that augments an existing parser with a character-level neural network.

Quantifying Urban Traffic Anomalies

no code implementations • 30 Sep 2016 • Zhengyi Zhou, Philipp Meerkamp, Chris Volinsky

Detecting and quantifying anomalies in urban traffic is critical for real-time alerting or re-routing in the short run and urban planning in the long run.