Paper: Composition Of Conditional Random Fields For Transfer Learning

ACL ID H05-1094
Title Composition Of Conditional Random Fields For Transfer Learning
Venue Conference on Empirical Methods in Natural Language Processing
Session Main Conference
Year 2005
Authors

Many learning tasks have subtasks for which much training data exists. Therefore, we want to transfer learning from the old, general- purpose subtask to a more specific new task, for which there is often less data. While work in transfer learning often considers how the old task should affect learning on the new task, in this paper we show that it helps to take into account how the new task affects the old. Specifically, we perform joint decoding of separately-trained sequence models, preserv- ing uncertainty between the tasks and allowing information from the new task to affect predic- tions on the old task. On two standard text data sets, we show that joint decoding outperforms cascaded decoding.