[Elsnet-list] Call for Participation: ACL Workshop on Incremental Parsing

Frank Keller keller at inf.ed.ac.uk
Tue Jun 8 18:56:05 CEST 2004

***** Call for Participation *****


Workshop at ACL-2004
Barcelona, Spain, July 25, 2004


Much recent parsing research has focused on the limited task of
achieving broad coverage and high accuracy in parsing Treebank
corpora. The parsing models developed for this task typically work on
a sentence-by-sentence basis: they often only deliver a valid analysis
if the input consists of a complete sentence. They are not designed to
operate incrementally, i.e., to deliver partial analyses (perhaps with
associated probabilities) that can be updated on a word-by-word basis
as more of the input becomes available.

Incrementality is desirable for two reasons. First, incremental
processing is crucial for many NLP tasks. Language modeling, for
instance, typically requires that probabilities are assigned
incrementally as more and more of the speech stream becomes
available. Recently, a number of parsing models have been proposed
that have this property and thus can be used for language
modeling. These models have resulted in lower perplexity scores and
word error rates than the standard n-gram models. However, the parsing
accuracy of these models typically falls short of the state of the
art. The challenge for parsing research is to develop models that
achieve optimal performance for both parsing and language modeling.

The second argument for incrementality comes from cognitive
modeling. There is substantial evidence showing that humans process
language in an incremental fashion. Any cognitively plausible model of
human parsing must take incrementality into account, and the modeling
literature contains considerable discussion on the relevant
computational mechanisms. Recently, a number of models of human
parsing have been proposed that are based on computational linguistic
approaches, such as PCFGs and related statistical models, suggesting a
potential synergy between cognitively and technologically motivated
parsing research.


09:10-09:35  Competence and Performance Grammar in Incremental
             Vincenzo Lombardo, Alessandro Mazzei and Patrick Sturt
09:35-10:00  Stochastically Evaluating the Validity of Partial Parse
             Trees in Incremental Parsing
             Yoshihide Kato, Shigeki Matsubara and Yasuyoshi Inagaki
0:30-11:20   Keynote talk: Efficient Incremental Beam-Search Parsing
             with Generative and Discriminative Models
             Brian Roark
11:20-11:45  Incremental Parsing with Reference Interaction
             Scott C. Stoness, Joel Tetreault and James Allen
11:45-12:10  Lookahead in Deterministic Left-Corner Parsing
             James Henderson
13:40-14:05  An Efficient Algorithm to Induce Minimum Average
             Lookahead Grammars for Incremental LR Parsing
             Dekai Wu and Yihai Shen
14:05-14:30  A Statistical Constraint Dependency Grammar (CDG) Parser 
             Wen Wang and Mary P. Harper
14:30-14:55  Incrementality in Deterministic Dependency Parsing
             Joakim Nivre
14:55-15:20  The Information-Processing Difficulty of Incremental
             John Hale
15:50-16:40  Keynote talk: Incrementality in Syntactic Processing:
             Computational Models and Experimental Evidence
             Patrick Sturt

Reserve Papers

Michael Daum: Dynamic Dependency Parsing

Matthew Purver and Ruth Kempson: Incremental Parsing, or Incremental

Shravan Vasishth and Richard L. Lewis: Modeling Sentence Processing in


To register for the workshop, please go to the following web site:


The early registration fee is EUR 70 for regular participants, and EUR
40 for students. The late registration fee is EUR 95 and EUR 65 for
regular participants and students, respectively. Note that there is an
additional fee for participants only attending the workshop, but not
the main ACL conference (see web site for details).

The deadline for early registration is June 20, 2004.


Frank Keller, University of Edinburgh
Stephen Clark, University of Edinburgh
Matthew Crocker, Saarland University
Mark Steedman, University of Edinburgh


The web site of the workshop is:


The organizers can be contacted at:

School of Informatics
University of Edinburgh
2 Buccleuch Place
Edinburgh EH8 9LW, UK
phone: +44-131-650-4407
fax:   +44-131-650-4587
email: acl04_workshop at inf.ed.ac.uk

More information about the Elsnet-list mailing list