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

Dialogue State Tracking on MultiWOZ 2.1 (test)

60.76Joint Goal Accuracy

ESAinsTOD (GT)

30.329638.229846.1354.0302Aug 31, 2021Jun 2, 2022Mar 4, 2023Dec 5, 2023Sep 5, 2024Jun 7, 2025Mar 10, 2026
Updated 4d ago

Evaluation Results

MethodLinks
2026.03
60.76----------------
2026.03
60.73----------------
2023.05
60.61----------------
2022.11
60.61----------------
2022.11
60.53----------------
2022.11
60.48----------------
2021.09
60.48----------------
2026.03
59.07----------------
2023.05
58.7----------------
2026.03
58.68----------------
2026.03
58.55----------------
2026.03
57.88----------------
2023.05
57.8----------------
2022.11
57.71------97.71---------
2023.05
57.5----------------
2023.05
57.45----------------
2022.11
57.45----------------
2026.03
57.45----------------
2023.05
57.26----------------
2023.05
57.1----------------
2021.09
56.85----------------
2026.03
56.85----------------
2026.03
56.74----------------
2022.11
56.7----------------
2023.05
56.66----------------
2022.11
56.66----------------
2021.09
56.66----------------
2023.05
56.45----------------
2021.09
56.39----------------
2022.11
56.36------97.59---------
2026.03
56.2----------------
2021.09
56.12----------------
2022.11
56.1----------------
2026.03
56.1----------------
2022.11
55.82------97.51---------
2026.03
55.76----------------
2021.09
55.72----------------
2021.08
55.7----------------
2021.09
55.37----------------
2021.08
55.35----------------
2023.05
55.3----------------
2021.08
55.3----------------
2022.11
55.29----------------
2021.09
55.29----------------
2026.03
55.29----------------
2022.11
55.26----------------
2022.11
55.23----------------
2021.09
55.23----------------
2026.03
55.23----------------
2023.05
54.97----------------
2022.11
54.86------97.55---------
2023.05
54.5----------------
2021.08
54.5----------------
2021.08
54.4----------------
2023.05
54.25----------------
2023.05
54.2----------------
2023.05
53.85----------------
2021.09
53.62----------------
2026.03
53.62----------------
2023.05
53.44----------------
2023.05
53.36----------------
2023.05
53.3----------------
2022.11
53.3------97.4---------
2026.03
53.3----------------
2022.11
53.19----------------
2021.08
53.1----------------
2023.05
53.02----------------
2022.11
53.01----------------
2021.08
52.8----------------
2023.05
52.57----------------
2026.03
52.57----------------
2021.08
52.5----------------
2023.05
52.08----------------
2023.05
51.68----------------
2026.03
51.21----------------
2023.05
51.2----------------
2021.08
51.2----------------
2021.08
51.2----------------
2023.05
51.17----------------
2021.09
50.95----------------
2021.08
50.3----------------
2023.05
50.14----------------
2023.05
49.88----------------
2026.03
49.67----------------
2021.08
49.2----------------
2022.11
49.01------96.76---------
2022.11
48.4------97.02---------
2026.03
48----------------
2023.05
46----------------
2023.05
46----------------
2022.11
45.6------96.55---------
2021.08
45.6----------------
2021.09
45.6----------------
2024.02
38.71-45.1563.1876.3969.4862.59-58.7781.8485.0791.0687.7390.16---
2024.02
38.56-37.5660.1274.4367.2961.31-67.1587.282.8690.2186.992.48---
2024.02
37.67-46.8360.2767.4860.959.54-62.2484.9985.3988.6980.3989.88---
2024.02
33.21-40.1559.0269.3160.6756.56-53.6779.5781.3687.8281.9589.45---
2024.02
32.11-38.4363.1874.156.257.68-56.581.9779.5291.1986.5690---
2024.02
31.84-38.4356.4469.1158.8255.41-54.2580.9979.9687.2683.3789.26---
2024.02
31.5-4255.870.960.856.44-52.7--------
Showing 100 of 138 rows