Domain Adaptation with Artificial Data for Semantic Parsing of Speech

We adapt a semantic role parser to the domain of goal-directed speech by creating an artificial treebank from an existing text tree-bank. We use a three-component model that includes distributional models from both target and source domains. We show that we improve the parser's performance on utterances collected from human-machine dialogues by training on the artificially created data without loss of performance on the text treebank.