Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Dialogue State Tracking on MultiWOZ 2.0 (test)

57.23Joint Goal Accuracy

ESAinsTOD (GT)

41.806845.810949.81553.8191Nov 10, 2022May 31, 2023Dec 20, 2023Jul 10, 2024Jan 28, 2025Aug 19, 2025Mar 10, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.03
57.23-
2026.03
56.93-
2026.03
55.9-
2022.11
55.4897.55
2026.03
55.03-
2026.03
54.92-
2022.11
54.8697.47
2022.11
54.53-
2022.11
54.5297.42
2022.11
54.39-
2026.03
54.39-
2022.11
54.3897.47
2022.11
53.89-
2026.03
53.89-
2026.03
53.2-
2026.03
53.17-
2026.03
52.68-
2026.03
52.59-
2022.11
52.4497.28
2026.03
52.24-
2022.11
52.23-
2026.03
52.1-
2022.11
51.72-
2026.03
51.38-
2026.03
51.36-
2022.11
51.17-
2026.03
51.17-
2022.11
48.6296.92
2022.11
42.4-