Cross-Lingual Information access, retrieval, extraction, ... needs, requirements and current state of the art

moderator: Khalid Choukri, ELDA - Evaluations and Language resources Distribution Agency
author: Jochen L. Leidner, Thomson Reuters
author: Allan Hanbury, Vienna University of Technology
author: Leonoor van der Beek, Q-go Europe
published: March 26, 2011,   recorded: December 2009,   views: 3503

See Also:

Download slides icon Download slides: mlia09_panel_information_01.pdf (51.2┬áKB)

Help icon Streaming Video Help

Related Open Educational Resources

Related content

Report a problem or upload files

If you have found a problem with this lecture or would like to send us extra material, articles, exercises, etc., please use our ticket system to describe your request and upload the data.
Enter your e-mail into the 'Cc' field, and we will keep you updated with your request's status.
Lecture popularity: You need to login to cast your vote.

 Watch videos:   (click on thumbnail to launch)

Watch Part 1
Part 1 03:23
Watch Part 2
Part 2 09:45
Watch Part 3
Part 3 08:47
Watch Part 4
Part 4 12:32


The main topics that were addressed were the following:

  • The needs of large users of multilingual information archives and their requirements, expectations
  • The current offers for enterprise search and web
  • What is preventing the take off of cross-lingual search applications

The theme of the panel discussion was why, despite 10 years of MLIA evaluations (within TREC, CLEF, NTCIR programmes), the adoption of such technologies is still a questionable issue. This session was organized around a series of questions which were circulated to the panelist beforehand. The list of questions was as follows:

  • During the last ten years or so, the number of languages and domains, for which research and development on MLIA have been conducted, has increased massively; is there any killer application that emerged from such clusters?
  • Have we managed to assess performance and are these in line with application deployments; are these two concepts strongly related (performance, deployments)?
  • Did the evaluations consider the right needs and requirements, and by the way do we have a clear picture of these?
  • If no success story can be mentioned today, does that mean key players were left out of these evaluations? Why?
  • If players were among the participants, does that mean we do have applications/core-technology with performances that can not be offered to real users?
  • And what offers do MLIA players have that one can highlight today, in particular for use by professionals?
  • Can we imagine fulfilling the needs of all languages and all domains at a reasonable cost (money, time, ...)?
  • How can the panelists (and the participants) address these issues and establish pointers to high levels of cooperation between users, service providers and core-technology providers (including computational linguistics?

Link this page

Would you like to put a link to this lecture on your homepage?
Go ahead! Copy the HTML snippet !

Write your own review or comment:

make sure you have javascript enabled or clear this field: