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

Git repo URL: git@github.com:poleval/2024-qa-task.git / Branch: main
Run git clone --single-branch git@github.com:poleval/2024-qa-task.git -b main to get the challenge data
Browse at https://github.com/poleval/2024-qa-task/tree/main

Leaderboard

#	submitter	when	ver.	description	test-A Score	test-B Score	×
1	[name not given]	2024-05-24 09:54	1.0.1 poleval-2024	test test	100.00	100.00	4
2	eNeLPol UJ AGH	2024-10-11 17:14	1.1.3 poleval-2024	4	83.76	82.92	5

#	tags	test-A Answerability	test-A Levenshtein	test-A Score	test-B Answerability	test-B Levenshtein	test-B Score
1	test	100.00	100.00	100.00	100.00	100.00	100.00
2		81.44	86.08	83.76	82.33	83.52	82.92
3	poleval-2024	50.72	67.98	59.35	45.86	66.53	56.19
4	baseline	50.72	67.98	59.35	45.86	66.53	56.19