Workshop on Shared Tasks and Comparative Evaluation in Natural Language Generation


The aim of this workshop is to bring together leading international researchers in the field of natural language generation (NLG), with the aim of establishing a clear, community-wide, position on the role of shared tasks and comparative evaluation in NLG research. There are many views held in the NLG community as to the proper role of evaluation, but so far there has been little scope to hammer out these positions in a forum that provides the time and involvement required to subject the different views to rigorous debate. Our aim is for this workshop to provide that forum. We expect the workshop to result in the working out of a number of clearly argued positions on the issue that will serve as a base resource for the field moving forward. Further, we expect that, in line with the wishes of a number in the community, basic specifications will be worked out for a variety of shared task evaluation campaigns that can then be considered by the wider community.