Recognizing Extended Spatiotemporal Expressions by Actively Trained Average Perceptron Ensembles

TL;DR

This paper introduces a new dataset and an ensemble learning approach using active training and average perceptron models to improve recognition of complex spatiotemporal expressions in text.

Contribution

It presents a novel dataset, a comparison of inference algorithms, a new active learning re-weighting method, and a joint parser for spatiotemporal expressions and named entities.

Findings

Ensemble model with Belief Propagation outperforms Viterbi decoding.

Active learning reduces annotation costs effectively.

The joint parser improves recognition of expanded spatiotemporal expressions.

Abstract

Precise geocoding and time normalization for text requires that location and time phrases be identified. Many state-of-the-art geoparsers and temporal parsers suffer from low recall. Categories commonly missed by parsers are: nouns used in a non- spatiotemporal sense, adjectival and adverbial phrases, prepositional phrases, and numerical phrases. We collected and annotated data set by querying commercial web searches API with such spatiotemporal expressions as were missed by state-of-the- art parsers. Due to the high cost of sentence annotation, active learning was used to label training data, and a new strategy was designed to better select training examples to reduce labeling cost. For the learning algorithm, we applied an average perceptron trained Featurized Hidden Markov Model (FHMM). Five FHMM instances were used to create an ensemble, with the output phrase selected by voting. Our ensemble model was tested on a range of sequential labeling tasks, and has shown competitive performance. Our contributions include (1) an new dataset annotated with named entities and expanded spatiotemporal expressions; (2) a comparison of inference algorithms for ensemble models showing the superior accuracy of Belief Propagation over Viterbi Decoding; (3) a new example re-weighting method for active ensemble learning that 'memorizes' the latest examples trained; (4) a spatiotemporal parser that jointly recognizes expanded spatiotemporal expressions as well as named entities.