This paper presents a novel framework called error case frames for correcting preposition errors.
This paper presents a novel framework for correcting preposition errors.
An error case frame consists of a verb, cases, and a feedback message as shown in Fig.
The method proposed here exploits two sources of corpus data: native and learner corpora.
Preposition errors are corrected by applying the generated error case frames to the target text.
We evaluated the proposed method from two points of View: correction performance and usefulness of feedback messages.
As the experimental results show, the proposed method achieves a comparable correction performance with the classifier-/SMT-based methods.
This paper presented a novel framework called error case frames for correcting preposition errors with feedback messages.
See all papers in Proc. ACL 2014 that mention F-measure.
See all papers in Proc. ACL that mention F-measure.
Back to top.