Featured Linguist!

Jost Gippert: Our Featured Linguist!

"Buenos dias", "buenas noches" -- this was the first words in a foreign language I heard in my life, as a three-year old boy growing up in developing post-war Western Germany, where the first gastarbeiters had arrived from Spain. Fascinated by the strange sounds, I tried to get to know some more languages, the only opportunity being TV courses of English and French -- there was no foreign language education for pre-teen school children in Germany yet in those days. Read more



Donate Now | Visit the Fund Drive Homepage

Amount Raised:

$34674

Still Needed:

$40326

Can anyone overtake Syntax in the Subfield Challenge ?

Grad School Challenge Leader: University of Washington


Publishing Partner: Cambridge University Press CUP Extra Publisher Login

FYI: Robust Interpretation Algorithms, Japanese ling


Author: Carolyn P Rose

FYI Body: A proposal is in preparation for a workshop to be held in conjunction
with the ANLP-NAACL 2000 conference in Seattle, Washington either
April 29, 30 or May 4. The workshop is entitled Robust Interpretation
For Real World Applications. The purpose of this message is to gauge
how much interest there is in this topic. Please review the proposal
below and email Carolyn Rose at rosecp@pitt.edu if you think you migh
be interested in participating in such a workshop. Feedback on the
proposal is also very welcome.

Thank you.

Carolyn Penstein Rose



Robust Interpretation for Real World Applications


The purpose of this proposed workshop is to explore the problem of
robust interpretation within the context of large-scale practical
applications. A great deal of attention has been focused in the pas
decade on the problem of building broad coverage knowledge sources
through a variety of automatic or semi-automatic means in order to
achieve a high level of performance. At all levels of interpretation,
however, from lexical level analysis to discourse level analysis, no
matter how complete the knowledge sources, the problem in practical
applications remains of applying necessarily incomplete linguistic and
world knowledge to noisy data. A great deal of work has been done
within specific sub-areas of computational linguistics to achieve
robustness for a specific task, such as parsing, speech act tagging,
or anaphora resolution. The purpose of this workshop is to bring
together researchers from separate areas of computational linguistics
who are all developing algorithms for robustness within those areas.
The focal question of this workshop is what are the common techniques
for robustness that have proven the most successful for several
specific interpretation problems? What would a unified approach to
robust interpretation look like that would achieve high levels of
robustness across all levels of interpretation?

The workshop will be organized into technical sessions with shor
paper presentations and group discussions, break out sessions
dedicated to specific topics, as well as panel discussions. Papers
are invited that describe new and innovative algorithms for achieving
robustness that have been evaluated on one or more interpretation
problems preferably within a large scale application. These papers
will be organized into technical sessions each targeting a general
approach, such as statistical, connectionist, or symbolic. A small
number of survey papers will also be accepted examining a spectrum of
previously developed approaches to achieving robustness for a specific
interpretation problem. Authors of accepted survey papers will be
invited to chair a panel discussion exploring alternative approaches
for handling their chosen interpretation problem.

Problems of interest for technical and survey papers include but are no
limited to:

- interpreting abbreviations
- interpreting sentences with unknown words
- interpreting idiomatic expressions
- interpreting sentences with real word spelling errors or
speech recognition errors
- parsing ungrammatical language
- interpreting vague or indirect language
- robust application of semantic selectional restrictions
- handling ellipsis and anaphora
- interpreting unexpected user initiatives







The Department of East Asian Studies at the University of Arizona offers
an M.A. program in Japanese linguistics/pedagogy and a Ph.D. program in
Japanese linguistics with specialization in discourse and grammar or
sociolinguistics. Financial aid is available. For program and application
information, visit http://w3.arizona.edu/~eas/ or contact: Yoshi Ono,
(520-621-5474; ono@u.arizona.edu) or Kimberly Jones (520-621-4417;
jonesk@u.arizona.edu).



Back   FYI main page