Cross-fertilization between human computer interaction and natural language processing: Why and how

Many of the central notions and ultimate goals of both human-computer interaction (HCI) and natural language processing (NLP) are common to both disciplines. Both are concerned with communication as a core concept, and both attempt to maximize the naturalness of this communication for the end-user. A central challenge to both disciplines is the issue of the choice and adaptation of the appropriate form of communication for the specific user and context at hand. Despite these strong commonalities, we observe very little collaboration, cross-references or even mutual knowledge between the HCI and NLP communities. And, surprisingly enough, although their goals might be very similar, the methods and the evaluation frameworks used in both research and applicative work in both areas are distinct. We think that it is time to step back and re-assess the potential for collaboration between the two disciplines. In this paper, we argue that importing ideas and methods from each discipline into the other can be fruitful, and we review specific areas where this is the case. We argue that cross-fertilization between HCI and NLP is desirable in wider and in more fundamental ways than only for the design of natural language interfaces. The reflection presented in this paper is motivated by our own work over the last four years in a team comprised of both HCI and specialists in natural language generation (NLG), a subfield of NLP specifically concerned with the automatic generation of language.