Version 2 (modified by 8 years ago) (diff) | ,
---|
Automatic language correction
IA161 Advanced NLP Course, Course Guarantee: Aleš Horák
Prepared by: Ján Švec
TODO til 31.5.2015
- choose particular papers for References below (that will serve as input for the lecture later on)
- prepare the Practical Session
State of the Art
References
Approx 3 current papers (preferably from best NLP conferences/journals, eg. ACL Anthology) that will be used as a source for the one-hour lecture:
- HLADEK, D, STAS, J, JUHAR, J. "Unsupervised Spelling Correction for the Slovak Text." Advances in Electrical and Electronic Engineering, 2013.
- paper2
- paper3
Practical Session
Concrete description of work assignment for students for the second one-hour part of the lecture. The work will consist of tasks connected with practical implementations of algorithms connected with the current topic (probably not the state-of-the-art algorithms mentioned in the first part) and with real data. Students can test the algorithms, evaluate them and possibly try some short adaptations for various subtasks.
Students can also be required to generate some results of their work and hand them in to prove completing the tasks.
Attachments (10)
- IMG_20151126_112640.jpg (1.6 MB) - added by 8 years ago.
- test-nopunct.txt (55.1 KB) - added by 6 years ago.
- tsd2014.pdf (131.3 KB) - added by 6 years ago.
- spell-testset1.txt (3.7 KB) - added by 6 years ago.
- spell-testset2.txt (7.3 KB) - added by 6 years ago.
- evalpunct_robust.py (1.8 KB) - added by 6 years ago.
- big.txt (6.2 MB) - added by 6 years ago.
-
spell.py (15.8 KB) - added by 3 years ago.
Spelling corrector
- eval-gold.txt (56.5 KB) - added by 3 years ago.
- punct.set (3.4 KB) - added by 3 years ago.