CLEF-2006 CL-SR at Maryland: English and Czech

The University of Maryland participated in the English and Czech tasks. For English, one monolingual run using only fields based on fully automatic transcription (the required condition) and one (otherwise identical) cross-language run using French queries were officially scored. Three contrastive runs in which manually generated metadata fields in the English collection were indexed were also officially scored to explore the applicability of recently developed "meaning matching" approaches to cross-language retrieval of manually indexed interviews. Statistical translation models trained on European Parliament proceedings were found to be poorly matched to this task, yielding 38% and 44% of monolingual mean average precision for indexing based on automatic transcription and manually generated metadata, respectively. Weighted use of alternative translations yielded an apparent (but not statistically significant) 7% improvement over one-best translation when bi-directional meaning matching techniques were employed. Results for Czech were not informative in this first year of that task, perhaps because no accommodations were made for the unique characteristics of Czech morphology.