Reporting Score Distributions Makes a Difference: Performance Study of LSTM-networks for Sequence Tagging.

In this paper we show that reporting a single performance score is insufficient to compare non-deterministic approaches. We demonstrate this for common sequence tagging tasks that the seed value for the random number generator can result in statistically significant (p u003c 10^{-4}) differences for state-of-the-art systems. For two recent systems for NER, we observe an absolute difference of one percentage point F1-score depending on the selected seed value, making these systems perceived either as state-of-the-art or mediocre. Instead of publishing and reporting single performance scores, we propose to compare score distributions based on multiple executions. Based on the evaluation of 50.000 LSTM-networks for five sequence tagging tasks, we present network architectures that perform superior as well as produce results with higher stability on unseen data.