Language Generation and Summarisation

Event Notification Type: 
Call for Papers
Abbreviated Title: 
Thursday, 6 August 2009
Submission Deadline: 
Friday, 1 May 2009

ACL-IJCNLP'09 Workshop on Language Generation and Summarisation


Language Generation and Summarisation (UCNLG+Sum) is a post-conference
workshop at ACL-IJCNLP 2009, Singapore, on 6 August 2009.


There are many branches of NLP research which involve the generation
of language (summarisation, MT, human-computer dialogue, application
front-ends, data-to-text generation, document authoring, etc.).
However, it is not always easy to identify common ground among the
generation components of these application areas, which has sometimes
made it difficult for generic research in `Natural Language
Generation' (NLG) to engage with them effectively. Recent advances in
corpus-based approaches across many of these areas, and in particular
in NLG itself, offer a new perspective on this problem and the
opportunity to explore synergies and differences from the common
grounding of corpus data.

This workshop is the third in an occasional series seeking to exploit
this opportunity by providing a forum for discussing NLG and its links
with these closely related fields from a corpus-oriented perspective.
These workshops 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 other fields of
research involving generation of language; and
3. to promote the sharing of data and methods in all research that
involves the generation of language.

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 XI in 2007) it was Language Generation and Machine
Translation. The special theme of the 2009 workshop is Language
Generation and Summarisation.

Aims of this Workshop

There are two basic approaches to text summarisation: abstractive,
where texts are analysed, and a more condensed version is regenerated,
and extractive, where key passages of the input texts themselves are
identified and then `glued together' to form a shorter text.
Extractive summarisation is less dependent on analysis and
regeneration techniques, but tends to produce summaries that are not
very coherent and whose referring expressions are not very clear (so
for example, extractive systems often score low on the DUC human
assessment criteria of Coherence and Referential Clarity).

The relevance of NLG techniques to abstractive summarisation is clear,
but recently there has also been increasing interest in regeneration
as a post-process for extractive summaries. Work by Otterbacher et
al., Steinberger et al. and Nenkova et al., for example, shows how
regeneration of (parts of) extractive summaries may help to increase
their coherence, referential clarity or fluency. At the same time, NLG
researchers are investigating techniques that could be used to improve
extractive summaries by regenerating them (in particular in the
subfield of referring expression generation, see for example the GREC
Shared Task papers at INLG 2008).

The core aim of this workshop is 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.

Topics of Interest

We invite submissions on all aspects of using corpora in the generation
of language, with a particular interest in relevance to text
summarisation. Specific topics include, but are not limited to:

- generation techniques in abstractive summarisation
- regeneration/rewriting/post-processing techniques for extractive
- generation of references to named entities in discourse context
- annotating corpora for language generation and summarisation
- uses of corpora in the evaluation of language generation and
summarisation systems
- reuse of corpus resources developed for NLU (e.g. treebanks) in
language generation and summarisation
- domain-specific vs. general-purpose corpora for language generation
and summarisation
- statistical approaches to language generation and summarisation
- machine learning methods for language generation and summarisation


Papers should describe original and unpublished work, emphasizing actual
rather than intended work, and should indicate clearly the state of
completion of the reported work. Wherever appropriate, concrete
evaluation results should be included. Papers that are being submitted
to other conferences or workshops should indicate this.

Submission information

Submissions should be no longer than 8 (eight) pages, and should follow
the ACL-IJCNLP 2009 guidelines using the style files provided at Papers
should be submitted in PDF format using the START submission website for
the workshop at The
deadline for submission is 1 May 2009.

Each paper will be reviewed by at least three programme committee
members. Final decisions on the technical programme will be made by
the workshop organisers.

As reviewing will be blind, papers should not include the authors'
names and affiliations. Self-references that reveal the authors'
identity, e.g., "We previously showed (Smith, 1991) ...", should be
avoided. Instead, use citations such as "Smith previously showed
(Smith, 1991) ...". Acknowledgments sections should be removed before


The proceedings of the workshop will be edited by the workshop
organisers and published by the ACL-IJCNLP 2009 conference organisers.

Important Dates

01 May 2009 Deadline for paper submissions
22 May 2009 Notification of acceptance to authors of workshop papers
07 June 2009 Camera-ready copies due
06 August 2009 UCNLG+SUM workshop in Singapore

Invited Speaker

Kathy McKeown, Columbia University, USA.

Panel on Common Ground between Summarisation and Language Generation

Panelists t.b.a.

GREC'09 Challenges Special Session

UCNLG+Sum will host the results session of this year's GREC Shared
Task Competitions which are part of the Generation Challenges
initiative. The first is the GREC-MSR (Main Subject Reference) Task
which uses the GREC-2.0 Corpus of 2,000 Wikipedia introduction
sections in which references to the main subject of the Wikipedia
article have been annotated, and the task is to develop a system that
can select (from a given list) an MSR that is appropriate in the
context. The second is the GREC-NEG (Named Entity Generation) Task
which uses the new GREC-People Corpus of 1,000 Wikipedia introduction
sections about people in which single and plural references to all
people mentioned in the text have been annotated. The task in GREC-NEG
is to select appropriate referential expressions for all mentions
(singular and plural) of people. For full details including the
GREC'09 call for participation, please go to the GREC'09 homepage at

Programme Committee

Enrique Alfonseca, Google Zurich, Switzerland
Srinivas Bangalore, AT&T, USA
Robert Dale, Macquarie University, Australia
Daniel Marcu, ISI, University of Southern California, USA
Chris Mellish, University of Aberdeen, UK
Ani Nenkova, University of Pennsylvania, USA
Amanda Stent, SUNY, USA
Michael Strube, EML Research, Germany
Stephen Wan, Macquarie University, Australia
Mike White, Ohio State University, USA
Jianguo Xiao, Peking University, China

Workshop organisers

Anja Belz, NLTG, University of Brighton, UK
Sebastian Varges, Information Engineering and Computer Science,
University of Trento, Italy
Roger Evans, NLTG, University of Brighton, UK

Workshop website

Contact email