Proceedings of the 2010 Workshop on Domain Adaptation for Natural Language Processing

Most modern Natural Language Processing (NLP) systems are subject to the well known problem of lack of portability to new domains and genres: there is a substantial drop in their performance when tested on data from a new domain, i.e., when test data is drawn from a related but different distribution from training data. This problem is inherent in the assumption of independent and identically distributed (i.i.d.) variables for machine learning systems, but has started to get attention only in recent years. The need for domain adaptation arises in almost all NLP tasks --- the goal of this workshop is to provide a meeting point for research that approaches the problem of adaptation from the varied perspectives of machine learning and a variety of NLP tasks. We believe there is much to gain by treating domain adaptation as a general learning strategy that utilizes prior knowledge of a specific or a general domain in learning about a new domain. Sharing insights, methodologies and successes across tasks will contribute towards a better understanding of this problem. To this end, this workshop presents original research in areas such as parsing, machine translation, dialog act tagging, entity recognition, summarization, etc. with the common theme of domain adaptation. We received sixteen submissions in all, out of which eight were selected for inclusion in the workshop.