Difference between revisions of "Event:B5691926-e33e-48aa-8066-2c39832e75e8"

From ConfIDent
(Created page with "{{Event |Title=2. Fachkonferenz Kinder- und Jugendbibliotheken |Ordinal=2 |In Event Series=Event Series:Dbc7071a-aa41-495a-8e00-29efb6b47934 |Single Day Event=no |Start Date=2...")
 
(mobo import Concept___Events-migrated)
Line 1: Line 1:
 
{{Event
 
{{Event
−
|Title=2. Fachkonferenz Kinder- und Jugendbibliotheken
+
|Acronym=Corpus Profiling 2008
−
|Ordinal=2
+
|Title=Corpus Profiling for Information Retrieval and Natural Language Processing Workshop
−
|In Event Series=Event Series:Dbc7071a-aa41-495a-8e00-29efb6b47934
+
|Type=Workshop
 +
|Homepage=kmi.open.ac.uk/events/corpus-profiling/index.php
 +
|City=London
 +
|Country=Country:GB
 +
|wikicfpId=3474
 +
|pageCreator=127.0.0.1
 +
|contributionType=1
 
|Single Day Event=no
 
|Single Day Event=no
−
|Start Date=2017/02/15
+
|Start Date=Oct 18, 2008
−
|End Date=2017/02/18
+
|End Date=Oct 18, 2008
 +
|Academic Field=Information Retrieval
 
|Event Status=as scheduled
 
|Event Status=as scheduled
 
|Event Mode=on site
 
|Event Mode=on site
−
|City=Remscheid
 
−
|Region=Nordrhein-Westfalen
 
−
|Country=Country:DE
 
 
}}
 
}}
 +
{{Event Deadline
 +
|Notification Deadline=Sep 12, 2008
 +
|Camera-Ready Deadline=Sep 26, 2008
 +
|Submission Deadline=Aug 15, 2008
 +
}}
 +
{{Event Deadline}}
 +
{{S Event}}
 +
 +
<pre>
 +
-----------------------------------
 +
PURPOSE
 +
-----------------------------------
 +
 +
We aim to bring together people from different research communities
 +
interested in exploring how corpus characteristics affect the behaviour
 +
of techniques in information retrieval and natural language processing,
 +
and to set out a roadmap for a shared research agenda.
 +
 +
It is well known in NLP and IR that the effectiveness of a technique
 +
depends on both the data on which it is deployed and its match with the
 +
task at hand. In 1973, Spärck-Jones attributed differing degrees of
 +
success at automatic classification to differences in dataset
 +
characteristics. Since Croft and Harper (1979), IR performance has
 +
repeatedly been related to collection size and other features, though no
 +
upper bound has been found.
 +
 +
The importance of data and task dependencies has been highlighted in IR,
 +
anaphora resolution, automatic summarization and recently, in word sense
 +
disambiguation. Many web/enterprise web retrieval systems rely on URL
 +
properties, link graph properties, click streams, and so on, with
 +
performance dependent on the degree to which this evidence is present
 +
and meaningful in a particular corpus.
 +
 +
Systematically exploring features that can be used effectively to
 +
characterise corpora, has been missing from IR/NLP research. This
 +
creates problems with replicability of experimental results and the
 +
development of applications.
 +
 +
The time is right to pursue this dependence systematically to address
 +
topics in tracking the effect of dataset profile on technique
 +
performance. Over the past 15 years, the approaches of several subject
 +
areas have converged with IR, as large corpora and test collections
 +
assume central importance in research methodologies. These areas have
 +
highlighted issues surrounding the role of data.
 +
 +
 +
-----------------------------------
 +
WORKSHOP FORMAT
 +
-----------------------------------
 +
 +
The workshop will be a day long, in conjunction with the Information
 +
Interaction in Context (IIiX'2008, http://irsg.bcs.org/iiix2008/). The
 +
workshop will have three components:
 +
 +
(1)  invited talks in the morning, introducing the background from
 +
different perspectives
 +
 +
(2) two afternoon sessions, presenting peer-reviewed papers
 +
 +
(3) a panel discussion (panel composed of presenters and the organizers).
 +
 +
 +
-----------------------------------
 +
TOPICS OF INTEREST
 +
-----------------------------------
 +
 +
We welcome original research or position papers. We particularly
 +
encourage postgraduate students or postdoctoral researchers to submit
 +
papers. Topics of interest include, but are NOT LIMITED to, the
 +
following areas:
 +
 +
    * Suitable features to characterise text/language variety,
 +
capturing known effects on technique performance with respect to a task;
 +
 +
    * Tasks that depend on aspects of corpus profiles, (e.g., the
 +
positive correlation of QA performance with fact frequency in a corpus);
 +
 +
    * Limitations of context-independent frequency-based measures, and
 +
exploration of measures that highlight complex dependencies;
 +
 +
    * Tools/techniques for characterising a feature or the extent to
 +
which it is manifested in a corpus;
 +
 +
    * Evaluation methodologies for testing feature candidates relative
 +
to task/technique;
 +
 +
    * Learnability of features (cf. meta-level learning for
 +
classification algorithms).
 +
 +
 +
-----------------------------------
 +
IMPORTANT DATES
 +
-----------------------------------
 +
 +
15 August 2008: Paper submission due
 +
 +
12 September 2008: Notification of acceptance/rejection
 +
 +
26 September 2008: Camera-ready due
 +
 +
18 October 2008: Workshop
 +
 +
 +
-----------------------------------
 +
SUBMISSION GUIDELINES
 +
-----------------------------------
 +
 +
Original technical papers, short papers and position papers are all
 +
welcome. Please ensure that your submission does not exceed 5,000 words
 +
in length. Use 10 point font size, double column for body text, and 12
 +
point bold for headings. Please send your submission in PDF to all the
 +
three organizers (A.Deroeck@open.ac.uk; d.song@open.ac.uk;
 +
udo@essex.ac.uk) with subject "Corpus Profiling workshop submission".
 +
 +
We will publish the accepted papers electronically through BCS's
 +
Electronic Workshops in Computing (eWiC), together with the extended
 +
abstracts of invited talks, a summary of the panel discussion. We will
 +
seek to pursue the research thread through further workshops at relevant
 +
conferences. We plan to organize a post-workshop special issue on a
 +
suitable IR or NLP related journal.
 +
 +
-----------------------------------
 +
PROGRAMME COMMITTEE
 +
-----------------------------------
 +
 +
Anne De Roeck (The Open University)
 +
Udo Kruschwitz (University of Essex)
 +
Ruslan Mitkov (University of Wolverhampton)
 +
Nikolaos Nanas (CERETETH, Greece)
 +
Michael Oakes (University of Sunderland)
 +
Ian Ruthven (University of Strathclyde)
 +
Dawei Song (KMi, The Open University)
 +
Tomek Strzalkowski (SUNY Albany)
 +
Alistair Willis (The Open University)
 +
 +
For further information please visit
 +
http://kmi.open.ac.uk/events/corpus-profiling/index.php
 +
</pre>This CfP was obtained from [http://www.wikicfp.com/cfp/servlet/event.showcfp?eventid=3474&amp;copyownerid=2 WikiCFP][[Category:Natural language processing]]
 +
[[Category:Information retrieval]]

Revision as of 18:43, 22 September 2022

Deadlines
2008-09-12
2008-09-26
2008-08-15
Deadlines
Venue

Remscheid, Nordrhein-Westfalen, Germany

Loading map...
-----------------------------------
PURPOSE
-----------------------------------

We aim to bring together people from different research communities
interested in exploring how corpus characteristics affect the behaviour
of techniques in information retrieval and natural language processing,
and to set out a roadmap for a shared research agenda.

It is well known in NLP and IR that the effectiveness of a technique
depends on both the data on which it is deployed and its match with the
task at hand. In 1973, Spärck-Jones attributed differing degrees of
success at automatic classification to differences in dataset
characteristics. Since Croft and Harper (1979), IR performance has
repeatedly been related to collection size and other features, though no
upper bound has been found.

The importance of data and task dependencies has been highlighted in IR,
anaphora resolution, automatic summarization and recently, in word sense
disambiguation. Many web/enterprise web retrieval systems rely on URL
properties, link graph properties, click streams, and so on, with
performance dependent on the degree to which this evidence is present
and meaningful in a particular corpus.

Systematically exploring features that can be used effectively to
characterise corpora, has been missing from IR/NLP research. This
creates problems with replicability of experimental results and the
development of applications.

The time is right to pursue this dependence systematically to address
topics in tracking the effect of dataset profile on technique
performance. Over the past 15 years, the approaches of several subject
areas have converged with IR, as large corpora and test collections
assume central importance in research methodologies. These areas have
highlighted issues surrounding the role of data.


-----------------------------------
WORKSHOP FORMAT
-----------------------------------

The workshop will be a day long, in conjunction with the Information
Interaction in Context (IIiX'2008, http://irsg.bcs.org/iiix2008/). The
workshop will have three components:

(1)  invited talks in the morning, introducing the background from
different perspectives

(2) two afternoon sessions, presenting peer-reviewed papers

(3) a panel discussion (panel composed of presenters and the organizers).


-----------------------------------
TOPICS OF INTEREST
-----------------------------------

We welcome original research or position papers. We particularly
encourage postgraduate students or postdoctoral researchers to submit
papers. Topics of interest include, but are NOT LIMITED to, the
following areas:

    * Suitable features to characterise text/language variety,
capturing known effects on technique performance with respect to a task;

    * Tasks that depend on aspects of corpus profiles, (e.g., the
positive correlation of QA performance with fact frequency in a corpus);

    * Limitations of context-independent frequency-based measures, and
exploration of measures that highlight complex dependencies;

    * Tools/techniques for characterising a feature or the extent to
which it is manifested in a corpus;

    * Evaluation methodologies for testing feature candidates relative
to task/technique;

    * Learnability of features (cf. meta-level learning for
classification algorithms).


-----------------------------------
IMPORTANT DATES
-----------------------------------

15 August 2008: Paper submission due

12 September 2008: Notification of acceptance/rejection

26 September 2008: Camera-ready due

18 October 2008: Workshop


-----------------------------------
SUBMISSION GUIDELINES
-----------------------------------

Original technical papers, short papers and position papers are all
welcome. Please ensure that your submission does not exceed 5,000 words
in length. Use 10 point font size, double column for body text, and 12
point bold for headings. Please send your submission in PDF to all the
three organizers (A.Deroeck@open.ac.uk; d.song@open.ac.uk;
udo@essex.ac.uk) with subject "Corpus Profiling workshop submission".

We will publish the accepted papers electronically through BCS's
Electronic Workshops in Computing (eWiC), together with the extended
abstracts of invited talks, a summary of the panel discussion. We will
seek to pursue the research thread through further workshops at relevant
conferences. We plan to organize a post-workshop special issue on a
suitable IR or NLP related journal.

-----------------------------------
PROGRAMME COMMITTEE
-----------------------------------

Anne De Roeck (The Open University)
Udo Kruschwitz (University of Essex)
Ruslan Mitkov (University of Wolverhampton)
Nikolaos Nanas (CERETETH, Greece)
Michael Oakes (University of Sunderland)
Ian Ruthven (University of Strathclyde)
Dawei Song (KMi, The Open University)
Tomek Strzalkowski (SUNY Albany)
Alistair Willis (The Open University)

For further information please visit
http://kmi.open.ac.uk/events/corpus-profiling/index.php

This CfP was obtained from WikiCFP

Retrieved from "https://www.confident-conference.org:443/index.php?title=Event:B5691926-e33e-48aa-8066-2c39832e75e8&oldid=70299"
Cookies help us deliver our services. By using our services, you agree to our use of cookies.
More information