headers
Nicola Stokes | 1 Sep 2005 12:00
Picon
Favicon

NICTA MSc and PhD Studentships University of Melbourne

MSc and PhD Studentships in Interactive Information Discovery and Delivery 
(I2D2)

NICTA Victoria Research Laboratory, University of Melbourne, Australia

http://nicta.com.au/director/research/programs/nip/research_activities/i2d2.cfm

National ICT Australia (NICTA) is Australia's Centre of Excellence in
Information and Communication Technology.  The NICTA Interactive
Information Discovery and Delivery Project is based in the Department
of Computer Science and Software Engineering at the University of
Melbourne.

The aim of the I2D2 project is to explore how intelligent linguistic and 
geospatial analysis of queries and content can enhance the ability of a
basic 
search engine to fullfill a user's information need. This project will 
involve the development of scalable and robust natural language processing, 
knowledge discovery, and information presentation technologies for
multimodal 
data on a variety of devices.

This project has funding for Masters and PhD scholarships in the
following core areas:

* geospatial and temporal expression recognition and resolution
* geospatial and temporal information retrieval and filtering
* interactive question-biased multi-document summarisation
* rhetorical structure, document structure and layout
* natural interaction, dialogue, speech, multimodality, user modelling
(Continue reading)

Permalink | Reply | 0 comments |
headers
HT_LING | 1 Sep 2005 19:15
Picon
Favicon

Rank open position in applied linguistics/corpus linguistics, Penn State University, USA

Posting for Jim Lantolf. Please contact him for any questions regarding this position.
______________________________________________________
PENN STATE
Department of Linguistics and Applied Language Studies

Rank open position for applied linguist specializing in corpus linguistics
with strong interest in languages other than English and in learner
corpora. Ph.D. required at time of appointment. Substantial research and
teaching record expected. For appointment at senior rank an outstanding
record in both areas is necessary. In addition to corpus linguistics, the
successful candidate will be expected to contribute to other areas within
the department's scope, including SLA, discourse analysis, language and
culture, language in use, language and health, language pedagogy. 

Send applications along with CV, three confidential letters of recommendation, 
no more than 3 sample publications and documentation of teaching excellence 
no later than November 11, 2005 to: 

James P. Lantolf
Chair, Search Committee 
Box  A 
305 Sparks Building
Penn State University 
University Park, PA 16802  
USA

Information about the department can be found at http://lals.la.psu.edu/ 
Penn State is committed to affirmative action, equal opportunity, and the diversity of its
workforce.
(Continue reading)

Permalink | Reply | 0 comments |
headers
Martin Krallinger | 2 Sep 2005 14:23
Picon
Picon

automatic definition construction/retrieval

Dear all,

I wonder if anybody could provide me with some advice related to tools 
or references related to the:

1) automatic construction of dictionary-like definitions of terms 
extracted automatically from free text articles, or alternatively

2) the retrieval of sentences which are likely to describe definitions 
of terms within documents would also be appreciated.

For instance a domain specific example could be :
[HpaB] : HpaB is a protein which promotes the secretion of a large set 
of effector proteins and prevents the delivery of non-effectors into the 
plant cell.

I am actually aware of the following reference:

 <at> Article{ Riloff:1993,
     author = {Riloff,E.},
     title = {{Automatically Constructing a Dictionary for Information 
Extraction Tasks.}},
     journal = { Proceedings of the Eleventh National Conference on 
Artificial Intelligence.},
     pages = {811--816},
     year = {1993},
}

Thanks for any advice and best regards,
(Continue reading)

Permalink | Reply | 11 comments |
headers
Yannick Versley | 2 Sep 2005 15:28
Picon
Favicon

Re: automatic definition construction/retrieval

> I wonder if anybody could provide me with some advice related to tools
> or references related to the:
>
> 1) automatic construction of dictionary-like definitions of terms
> extracted automatically from free text articles, or alternatively
> 2) the retrieval of sentences which are likely to describe definitions
> of terms within documents would also be appreciated.
I think this has much in common with the problem of answering definition 
questions in question answering. I would think that
Hildebrandt/Katz/Lin (2003): Answering Definition Questions
		Using Multiple 	Knowledge Sources
(http://acl.ldc.upenn.edu/hlt-naacl2004/main/pdf/137_Paper.pdf)
could be a good starting point.

If you want to get something as in your example:
> [HpaB] : HpaB is a protein which promotes the secretion of a large set
> of effector proteins and prevents the delivery of non-effectors into the
> plant cell.
a good start could be to use a list of upper-level terms like "protein", 
"amino acid" etc. as well as action verbs and then scan the text for patterns 
like
HpaB, [NP], [NP] and other [Hypernym-NP]s
as well as
HpaB [VP [action verb] ...]
For reference, see e.g.
Hearst, M.(1992): Automatic Acquisition of Hyponyms from Large Text Corpora
(see http://www.sims.berkeley.edu/~hearst/publications.html)
or
R. Girju, A. Badulescu, and D. Moldovan (2000):
Learning Semantic Constraints for the Automatic Discovery of Part-Whole
(Continue reading)

Permalink | Reply | 2 comments |
headers
Nina Wacholder | 2 Sep 2005 15:47
Picon
Favicon

Re: automatic definition construction/retrieval

Judith Klavans has done a lot of work on this problem.

See:
Muresan, Smaranda, Samuel D. Popper, Peter T. Davis, Judith L. Klavans 
(2003). “Building a Terminological Database from Heterogeneous 
Definitional Sources”. /Proceedings of the National Conference on 
Digital Government Research/. Boston, Massachusetts.

Klavans, Judith L., Peter T. Davis and Samuel Popper (2002). “Building 
Large Ontologies using Web Crawling and Glossary Analysis Techniques”. 
/Proceedings of the National Conference for Digital Government 
Research/. Los Angeles, California.

Muresan, Smaranda, and Judith L. Klavans (2002). “A Method for 
Automatically Building and Evaluating Dictionary Resources”. 
/Proceedings of the Language Resources and Evaluation Conference/ (LREC 
2002). Las Palmas, Spain.

Klavans, Judith L. and Smaranda Muresan (2001a) "Evaluation of DEFINDER: 
A System to Mine Definitions from Consumer-oriented Medical Text", in 
Proceedings of the First ACM/IEEE-CS Joint Conference on Digital 
Libraries (JCDL). Roanoke, Virginia, pp. 201-203.

Klavans, Judith L. and Smaranda Muresan (forthcoming 2001b) "Evaluation 
of the DEFINDER System for Fully Automatic Glossary Construction", in 
Proceedings of the American Medical Informatics Association (AMIA) 
Symposium. Washington, D.C.

Martin Krallinger wrote:
(Continue reading)

Permalink | Reply | 0 comments |
headers
Yannick Versley | 2 Sep 2005 16:16
Picon
Favicon

Re: automatic definition construction/retrieval

> R. Girju, A. Badulescu, and D. Moldovan (2000):
> Learning Semantic Constraints for the Automatic Discovery of Part-Whole
> Relations
> R. Girju(2003):
> Automatic Detection of Causal Relations for Question Answering
> (see Automatic Detection of Causal Relations for Question Answering)
sorry, that was meant to be
(see http://cs.baylor.edu/~girju/papers/papers.html)

best regards, Yannick Versley
Permalink | Reply | 0 comments |
headers
Carlos Rodriguez | 2 Sep 2005 18:22
Picon

[Fwd: Re: automatic definition construction/retrieval]


Hi Martin,

I don't know if Riloff's work will be useful to you, if you are looking 
for classic, lexicographic definitions, since she works on Information 
Extraction "dictionaries", or sets of useful extraction patterns for 
specific tasks. If you are loking foe metalinguistic patterns, see below.
For a good description of definitional contexts, see:

Pearson, J. (1998) /Terms in Context./ Studies in Corpus Linguistics. 
John Benjamins. Amsterdam

Two lines of work that are actual implementations come to mind, one by 
Klavans, J. and Muresan, S. (2001) Evaluation of the DEFINDER System for 
Fully Automatic Glossary Construction, /Proc. Am. Med. Inf. Ass. //Symp./

The other, my own: Rodríguez, C. (2004)  Metalinguistic Information 
Extraction for Terminology,/ 3rd International Workshop on Computational 
Terminology/ (CompuTerm 2004) Coling, Geneve 2004.

Good luck

- 
Carlos Rodríguez Penagos

CRodriguezP <at> turing.iimas.unam.mx
http://turing.iimas.unam.mx/~crodriguezp/
Instituto de Investigaciones en Matemáticas Aplicadas y en Sistemas
Institute of Research in Applied Mathematics and Systems
UNAM National Autonomous University, México
(Continue reading)

Permalink | Reply | 501 comments |
headers
Hristo Tanev | 2 Sep 2005 18:49
Picon
Favicon

Re: automatic definition construction/retrieval

Mr. Krallinger,

May be this paper will be of interest for you:

Hristo Tanev, Milen Kouylekov, Bernardo Magnini,
Matteo Negri, Bonaventura Coppola "Multilingual
Pattern Libraries for Question Answering: a Case Study
for Definition Questions" 
In proceedings of LREC 2004, Lisbon, Portugal. 2004,
Vol 6 pages 1935-1938. 

Best regards,
Hristo Tanev

		
___________________________________________________________ 
How much free photo storage do you get? Store your holiday 
snaps for FREE with Yahoo! Photos http://uk.photos.yahoo.com
Permalink | Reply | 0 comments |
headers
Ken Litkowski | 2 Sep 2005 19:07

Re: [Fwd: Re: automatic definition construction/retrieval]

While it may be the case that some single word new words arise and need 
definition, I would suggest that most of them will be multiword units. 
HpaB is probably an abbreviation for a longer MWU.  While some of the 
definition seeking behavior evolving in the TREC QA track is certainly 
relevant, that is not "defining" in the lexicographical sense.

An important useful first step these days is the use of the Google 
'define' operator to pick whatever formal definitions might exist. 
Next, one can Google "HpaB is" and get a whole range of answers.

But, creating new definitions is the more interesting part of the 
problem, particularly with MWUs.  For this, I would suggest the work of 
OntoLearn (Velardi and Navigli).  There was a recent article in 
Computational Linguistics, and they have several other papers which 
describe algorithms for inducing definitions.  Keep an eye out for 
further progress from them.

	Ken
--

-- 
Ken Litkowski                     TEL.: 301-482-0237
CL Research                       EMAIL: ken <at> clres.com
9208 Gue Road
Damascus, MD 20872-1025 USA       Home Page: http://www.clres.com
Permalink | Reply | 501 comments |
headers
Mark Sanderson | 2 Sep 2005 19:49
Picon
Favicon

Re: automatic definition construction/retrieval

Here's another one:

Joho, H. & Sanderson, M. (2000) Retrieving Descriptive Phrases from 
Large Amounts of Free Text, in proceedings of the 9th ACM Conference 
on Information and Knowledge Management, Pages 180-186

You can download it from here

         http://dis.shef.ac.uk/mark/cv/publications/papers/my_papers/CIKM00.pdf

At 14:28 02/09/2005, Yannick Versley wrote:
> > I wonder if anybody could provide me with some advice related to tools
> > or references related to the:
> >
> > 1) automatic construction of dictionary-like definitions of terms
> > extracted automatically from free text articles, or alternatively
> > 2) the retrieval of sentences which are likely to describe definitions
> > of terms within documents would also be appreciated.
>I think this has much in common with the problem of answering definition
>questions in question answering. I would think that
>Hildebrandt/Katz/Lin (2003): Answering Definition Questions
>                 Using Multiple  Knowledge Sources
>(http://acl.ldc.upenn.edu/hlt-naacl2004/main/pdf/137_Paper.pdf)
>could be a good starting point.
>
>If you want to get something as in your example:
> > [HpaB] : HpaB is a protein which promotes the secretion of a large set
> > of effector proteins and prevents the delivery of non-effectors into the
> > plant cell.
>a good start could be to use a list of upper-level terms like "protein",
(Continue reading)

Permalink | Reply | 0 comments |

Gmane