Azzah Al-Maskari

The effect of user characteristics on search effectiveness in information retrieval

This paper investigates the influence of user characteristics (e.g. search experience and cognitive skills) on user effectiveness. A user study was conducted to investigate this effect, 56 participants completed searches for 56 topics using the TREC test collection. Results indicated that participants with search experience and high cognitive skills were more effective than those with less experience and slower perceptual abilities. However, all users rated themselves with the same level of satisfaction with the search results despite the fact they varied substantially in their effectiveness. Therefore, information retrieval evaluators should take these factors into consideration when investigating the impact of system effectiveness on user effectiveness.

Relevance judgments between TREC and Non-TREC assessors

This paper investigates the agreement of relevance assessments between official TREC judgments and those generated from an interactive IR experiment. Results show that 63% of documents judged relevant by our users matched official TREC judgments. Several factors contributed to differences in the agreements: the number of retrieved relevant documents; the number of relevant documents judged; system effectiveness per topic and the ranking of relevant documents.

Providing multilingual access to flickr for Arabic users

In this paper we describe our submission for iCLEF2006: an interface that allows users to search FLICKR in Arabic for images with captions in a range of languages. We report and discuss the results gained from a user experiment in accordance with directives given by iCLEF, including an analysis of the success of search tasks. To enable the searching of multilingual image annotations we use English as an interlingua. An Arabic-English dictionary is used for initial query translation, and then Babelfish is used to translate between English and French, German, Italian, Dutch and Spanish. Users are able to modify the English version of the query if they have the necessary language skills to do so. We have chosen to experiment with Arabic retrieval from FLICKR due to the growing numbers of online Middle Eastern users, the limited numbers of interactive Arabic user studies for cross-language IR to date, and the availability of resources to undertake a user study.

The affect of machine translation on the performance of Arabic-English QA system

The aim of this paper is to investigate how much the effectiveness of a Question Answering (QA) system was affected by the performance of Machine Translation (MT) based question translation. Nearly 200 questions were selected from TREC QA tracks and ran through a question answering system. It was able to answer 42.6% of the questions correctly in a monolingual run. These questions were then translated manually from English into Arabic and back into English using an MT system, and then re-applied to the QA system. The system was able to answer 10.2% of the translated questions. An analysis of what sort of translation error affected which questions was conducted, concluding that factoid type questions are less prone to translation error than others.