Watermarking the Outputs of Structured Prediction with an application in Statistical Machine Translation

We propose a general method to watermark and probabilistically identify the structured outputs of machine learning algorithms. Our method is robust to local editing operations and provides well defined trade-offs between the ability to identify algorithm outputs and the quality of the watermarked output. Unlike previous work in the field, our approach does not rely on controlling the inputs to the algorithm and provides probabilistic guarantees on the ability to identify collections of results from one’s own algorithm. We present an application in statistical machine translation, where machine translated output is watermarked at minimal loss in translation quality and detected with high recall. 1 Motivation Machine learning algorithms provide structured results to input queries by simulating human behavior. Examples include automatic machine translation (Brown et al., 1993) or automatic text and rich media summarization (Goldstein et al., 1999). These algorithms often estimate so...

• Type: Journal
• Year: 2011
• Where: EMNLP
• Authors: Ashish Venugopal, Jakob Uszkoreit, David Talbot, Franz Josef Och, Juri Ganitkevitch
• Keywords: Automatic Machine Translation, EMNLP 2011, Input Queries, Natural Language Processing, Statistical Machine Translation