Learning to Speed Up Structured Output Prediction
This work addresses the challenge of slow prediction times in structured output tasks for machine learning practitioners, though it is incremental as it builds on existing learning-to-search approaches.
The paper tackles the problem of computationally expensive structured output prediction by training a speedup classifier to mimic a black-box classifier, reducing prediction time without accuracy loss, as demonstrated on entity and relation extraction tasks where it outperforms greedy search in speed.
Predicting structured outputs can be computationally onerous due to the combinatorially large output spaces. In this paper, we focus on reducing the prediction time of a trained black-box structured classifier without losing accuracy. To do so, we train a speedup classifier that learns to mimic a black-box classifier under the learning-to-search approach. As the structured classifier predicts more examples, the speedup classifier will operate as a learned heuristic to guide search to favorable regions of the output space. We present a mistake bound for the speedup classifier and identify inference situations where it can independently make correct judgments without input features. We evaluate our method on the task of entity and relation extraction and show that the speedup classifier outperforms even greedy search in terms of speed without loss of accuracy.