Reading Comprehension

Question Answering is an important and broad field of research within Natural Language Processing. Previous editions of PolEval included passage retrieval tasks, which are crucial in narrowing down the range of documents relevant to a human question, but only after including a reading comprehension system, can the whole process of answering a question be fully automated. [ver. 1.1.3]

Deadline: 2024-10-28 23:59:00 UTC

poleval-2024

# submitter when ver. description dev-0 Score test-A Score test-B Score
4 eNeLPol UJ AGH 2024-10-14 15:34 1.1.3 poleval-2024 5 80.43 82.36 80.09
3 eNeLPol UJ AGH 2024-10-11 17:14 1.1.3 poleval-2024 4 83.07 83.76 82.92
6 [name not given] 2024-09-19 13:19 1.1.3 poleval-2024 test poleval-2024 15.52 59.35 56.19
7 eNeLPol UJ AGH 2024-08-08 20:00 1.0.4 poleval-2024 3 15.51 14.84 15.81
9 eNeLPol UJ AGH 2024-08-08 19:37 1.0.4 poleval-2024 2 6.29 N/A 4.97
8 eNeLPol UJ AGH 2024-08-08 19:29 1.0.4 poleval-2024 1 68.01 7.35 4.97
2 [name not given] 2024-05-24 09:57 1.0.1 poleval-2024 test error test 100.00 99.97 99.89
1 [name not given] 2024-05-24 09:54 1.0.1 poleval-2024 test test 100.00 100.00 100.00
5 [name not given] 2024-05-23 15:29 1.0.0 poleval-2024 test baseline 15.52 59.35 56.19