Skip to main content

Table 4 Detailed results on BEA-19

From: A multi-task learning framework for efficient grammatical error correction of textual messages in mobile communications

Work

Evaluation aspect

P

R

\(\user2{F}_{{{\mathbf{0}}{\mathbf{.5}}}}\)

Our approach(SpanBERT)

Span-level correction

57.8

50.4

56.1

Span-level detection

78.2

63.6

74.8

Token-level detection

88.0

66.7

82.7

GECToR[12]

Span-level correction

64.2

47.0

59.8

Span-level detection

75.2

52.4

69.2

Token-level detection

84.4

54.2

76.0