Special Issue of Computational Linguistics: Anaphora and Ellipsis Resolution
Guest editors: Ruslan Mitkov, Branimir Boguraev, Shalom Lappin
Anaphora and ellipsis both account for cohesion in text and are phenomena
of active study in formal and computational linguistics alike. The
correct interpretation of anaphora and ellipsis, as well as the
understanding of the relationship between them, is vital for Natural
Language Processing.
After considerable initial research, and after years of relative silence
in the early eighties, these issues have attracted the attention of many
researchers in the last 10 years and much promising work on the topic has
been reported. Discourse-orientated theories and formalisms such as DRT
and Centering have inspired new research on the computational treatment
of anaphora. The drive towards corpus-based robust NLP solutions has
further stimulated interest, for alternative and/or data-enriched
approaches. In addition, application-driven research in areas such as
automatic abstracting and information extraction, has independently
identified the importance of (and boosted the research in) anaphora and
coreference resolution. Ellipsis resolution too, being of particular
importance to a number of Natural Language Understanding applications
such as dialogue and discourse processing, has received increasing
attention. The growing interest in anaphora and ellipsis resolution has
been demonstrated clearly over the last 4--5 years through the MUC
coreference task projects and at a number of related fora (workshops,
conferences, etc.).
Against this background of expanding research and growing interest, this
special issue offers the opportunity for a high quality, and timely,
collection of papers on anaphora and ellipsis resolution.
Topics
The call for papers invites submissions of papers describing recent novel
and challenging work/results in anaphora and ellipsis resolution.
The range of topics to be covered will include, but will not be limited
to:
o new anaphora and ellipsis resolution algorithms,
o factors in anaphora resolution: salience and interaction of factors,
o techniques in ellipsis resolution,
o use of theories and formalisms in anaphora resolution,
o use of theories and formalisms in ellipsis resolution,
o applications of anaphora/coreference resolution,
o applications of ellipsis resolution,
o multilingual anaphora resolution,
o evaluation issues,
o use/production of annotated corpora for anaphora and ellipsis.
In addition, we expect papers addressing various issues of debate related
to the resolution of anaphora and ellipsis, such as:
o Is it possible to propose a core set of factors used in anaphora
resolution?
o When dealing with real data, is it at all possible to posit
"constraints", or should all factors be regarded as "preferences"?
o What is the case for languages other than English?
o What degree of preference (weight) should be given to "preferential"
factors? How should weights best be determined? What empirical
data can be brought to bear on this?
o What would be an optimal order for the application of multiple
factors? Would this affect the scoring strategies used in selecting
the antecedent?
o Is it realistic to expect high precision over unrestricted texts?
o Is it realistic to determine anaphoric links in corpora
automatically?
o Are all CL applications 'equal' with respect to their requirements
from an anaphora resolution module? What kind(s) of compromises
might be possible, depending on the NLP task, and how would
awareness of these affect the tuning of a resolution algorithm for
particular type(s) of input text?
o Should ellipsis resolution be handled by syntactic or semantic
reconstruction?
o Is it necessary to retrieve both syntactic and semantic properties of
the antecedent in the reconstructed representation of the elided
structure?
Finally, we invite discussion on various open questions from both
theoretical and computational point of view such as whether we should
construe ellipsis as entirely distinct from anaphora.
Submissions and Reviewing
The submission deadline is 1 April 2000. Authors can submit either
electronically or send 6 hard copies of their paper (for format and style
details, see http://www.aclweb.org/cl) to:
Ruslan Mitkov (R.Mitkov@wlv.ac.uk)
School of Humanities, Languages and Social Sciences
University of Wolverhampton
Stafford St.
Wolverhampton WV1 1SB
United Kingdom
Please note that in addition to the submission, a 100-word abstract and
details of the author (following the format given at
http://www.aclweb.org/cl/submit.txt) should be emailed to R.Mitkov.
Each submission will be reviewed both by experts appointed by the editor
of the journal and by members of the guest editorial board of the special
issue. In addition to the guest editors,
Ruslan Mitkov (University of Wolverhampton),
Branimir Boguraev (IBM Research, Yorktown Heights) and
Shalom Lappin (University of London),
the editorial board includes the following members:
Nicholas Asher (University of Texas),
Amit Bagga (GE CRD),
Claire Cardie (Cornell University),
David Carter (Speech Machines, Malvern),
Eugene Charniak (Brown University),
Walter Daelemans (University of Antwerp),
Mary Dalrymple (Xerox PARC),
Dan Hardt (Villanova University),
Graeme Hirst (University of Toronto),
Jerry Hobbs (SRI International),
Aravind Joshi (University of Pennsylvania),
Lauri Karttunen (Xerox Research Center Europe),
Andrew Kehler (SRI International),
Christopher Kennedy (Northwestern University),
Massimo Poesio (University of Edinburgh),
Monique Rolbert (University of Marseille),
Stuart Shieber (Harvard University),
Candy Sidner (Lotus Research),
Marilyn Walker (AT&T).