Proceedings of the 2009 Workshop on Language Generation and Summarisation (UCNLG+Sum 2009)

The Workshop on Language Generation and Summarisation (UCNLG+MT) took place in Singapore on 6th August 2009, as part of ACL-IJCNLP’09. It was the third of the UCNLG workshops which have the general aims 1. to provide a forum for reporting and discussing corpus-oriented methods for generating language; 2. to foster cross-fertilisation between NLG and related fields by looking for common ground through corpus-oriented approaches; and 3. to promote the sharing of data and methods in all language generation research. Each of these workshops has a special theme: at the first workshop (at Corpus Linguistics in 2005) it was the use of corpora in NLG, at the second (at MT Summit in 2007) it was Language Generation and Machine Translation. The special theme of this third UCNLG workshop was Language Generation and Text Summarisation. The core aim was to provide a forum for NLG and summarisation researchers to examine the similarities and differences between their current approaches to generating language, and to explore the potential for cross-fertilisation and the extent to which resources and techniques can be shared between the NLG and summarisation fields. The call for papers issued at the end of January 2009 elicited a good number of high-quality submissions, each of which was peer-reviewed by three members of the programme committee. The interest in the workshop from leading researchers in both fields and the quality of submissions was high, so we aimed to be as inclusive as possible within the practical constraints of the workshop. In the end we accepted six submissions as long papers and four as short papers. The resulting workshop programme packed a lot of exciting content into one day. We were delighted to start the workshop with a keynote presentation from Prof Kathy McKeown, one of the most eminent researchers in NLG and its application to summarisation. Our technical programme included papers on structuring abstracts (Saggion), selecting content for summaries (Cheung, Carenini and Ng), sentence compression (Xu and Grishman; Cordiero, Dias and Brazdil), sentence revision for summarisation (Tanaka et al.), evaluating summaries (Owczarzak and Dang), corpus-based generation of directions (Schuldes et al.), reducing redundancy in summarisation (Hendrickx et al.), generation of narrative content (Caropreso et al.) and summarisation of non-textual content (Kumar et al.). The programme also included a session reporting the results of the Generation of Referring Expressions in Context (GREC) shared task evaluations (part of the Generation Challenges 2009 initiative), and still had space for a general discussion on synergies between NLG and summarisation. We would like to thank all the people who have contributed to the organisation and delivery of this workshop: the authors who submitted such high quality papers; the programme committee for their prompt and effective reviewing; our keynote speaker, Kathy McKeown; our panelists (at the time of writing), Ed Hovy, Kathy McKeown and Donia Scott; the ACL-IJCNLP 2009 Organising Committee, especially the workshop chairs, Jimmy Lin and Yuji Matsumoto, and Jing-Shin Chang; all the particpants in the workshop and future readers of these proceedings for your shared interest in this exciting area of research