Table 6.
LiveQA Measures: Average Score (main score), Success@i+ and Precision@i+ on LiveQA’17 Test Data
Measures | IR-based System | IR+RQE System | LiveQA’17 Best Results | LiveQA’17 Median Results |
---|---|---|---|---|
avgScore(0-3) | 0.711 | 0.827 | 0.637 | 0.431 |
succ@2+ | 0.442 | 0.461 | 0.392 | 0.245 |
succ@3+ | 0.192 | 0.25 | 0.265 | 0.142 |
succ@4+ | 0.077 | 0.115 | 0.098 | 0.059 |
prec@2+ | 0.46 | 0.475 | 0.404 | 0.331 |
prec@3+ | 0.2 | 0.257 | 0.273 | 0.178 |
prec@4+ | 0.08 | 0.119 | 0.101 | 0.077 |
Evaluation of the first retrieved answer for each question. N.B. Evaluating the RQE System alone is not relevant as explained previously (“RQE-based QA Approach” section). The best score are in bold