Title | ||
---|---|---|
Better hypothesis testing for statistical machine translation: controlling for optimizer instability |
Abstract | ||
---|---|---|
In statistical machine translation, a researcher seeks to determine whether some innovation (e.g., a new feature, model, or inference algorithm) improves translation quality in comparison to a baseline system. To answer this question, he runs an experiment to evaluate the behavior of the two systems on held-out data. In this paper, we consider how to make such experiments more statistically reliable. We provide a systematic analysis of the effects of optimizer instability---an extraneous variable that is seldom controlled for---on experimental outcomes, and make recommendations for reporting results more accurately. |
Year | Venue | Keywords |
---|---|---|
2011 | ACL (Short Papers) | translation quality,statistical machine translation,held-out data,extraneous variable,inference algorithm,hypothesis testing,baseline system,new feature,experimental outcome,systematic analysis,optimizer instability |
Field | DocType | Volume |
Computer science,Inference,Machine translation,Artificial intelligence,Natural language processing,Baseline system,Statistical hypothesis testing,Machine learning | Conference | P11-2 |
Citations | PageRank | References |
202 | 4.94 | 25 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jonathan H. Clark | 1 | 411 | 16.42 |
chris dyer | 2 | 5438 | 232.28 |
alon lavie | 3 | 2606 | 177.91 |
Noah A. Smith | 4 | 5867 | 314.27 |