For the first interactice Cross Language Evaluations Forum, the Maryland team focused on comparison of term-of term gloss translation with full machine translataion for the document selection task. The results show that (1) searchers are able to make relevance judgments with translations form either approach, and (2) the machine translation system achieved better effeciveness that ahe gloss translation strategy that so we tried. although the differnce is not statiscally segnificant. It was noted that the "someWhat relevant" category was used differently by seachers presented with gloss translations than with machine translations, and some reasons for the difference are suggested . Finally, the results suggest that the F measure used in this evaluation is better suited for use with topics have many known relevant document than those with few