Home > Tasks 2017

Tasks 2017

The overall usage scenario for this lab edition is centered on festival participants:

  1. an insider participant who receives a microblog about the cultural event in which he will participate in will need context to understand it (microblogs often contain implicit information). The participant will also need this background information before clicking on the link.
  2. if a participant in a specific location wants to know what is going on in surrounding events relative to artists, music or shows that he would like to see. Starting from a list of bookmarks in the wikipedia app, the participant will seek for a short list of microblogs summarizing the current trends about related cultural events. She/he is more interested in microblogs from insiders than outsiders or officials.

Three independent sub-tasks have been identified: content analysis, global search and time-line summarization.

  • Microblog Cultural Contextualization 2017 lab introduction
    18 October 2016, by sanjuan

    These are the slides used to presented at CLEF 2016 in Evora to introduce the CM2 lab. Overall Procedure Take a microblog about an event with an url. Identify its language. Identify a related cultural event or filter it out. Reveal When, Where, Who ... Relate it to Wikipedia entities2017 Organization Task 1: language, filtering and localization lead by Toulouse, Montréal and Paris starts … now! Task 2: entity extraction, summarization and linking starts in November 2016 lead by Avignon, (…)

  • Evaluation Methodology
    2 November 2015, by sanjuan

    Systems will be evaluated mainly on informativeness and relevance, but readability and ergonomy will be also checked. Informativeness evaluation will rely on textual references established by experts in project GAFES, following the strict methodology
    at CLEF-INEX tweet contextualization track (http://inex.mmci.uni-saarland.de/tracks/qa/). Readability and ergonomy would be carried out on the output for specific festivals based on questionnaires to be filled out by lab participants. Best (…)