Skip to Main Content
Table 19

State-of-the-art systems on CoNLL-2014 data set. The systems are divided into three categories: classifiers, MT, and combined. For each system, we also show the size of the annotated learner data used to train the system. Depending on the type of training data available, a specific approach should be preferred. In particular, classification systems can be trained from significantly less annotated data and can focus on specific errors, whereas MT-based systems do not have this capability. Best result in each category is in bold.

System typeSystem nameAnnotated learner dataF0.5
CoNLLLang-8CLC
1.2M11-48M29M
Classif. Susanto, Phandi, and Ng (2014) ✓   35.44 
Rozovskaya and Roth (2016) ✓   43.11 
 
MT Mizumoto and Matsumoto (2016) ✓ ✓  40.00 
Yuan and Briscoe (2016) ✓  ✓ 39.90 
Chollampatt, Taghipour, and Ng (2016) ✓ ✓  41.75 
Hoang, Chollampatt, and Ng (2016) ✓ ✓  41.19 
Rozovskaya and Roth (2016) ✓   28.25 
Rozovskaya and Roth (2016) ✓ ✓  39.48 
Junczys-Dowmunt and Grundkiewicz (2016) ✓ ✓  49.49 
 
Combined Susanto, Phandi, and Ng (2014) ✓ ✓  39.39 
Rozovskaya and Roth (2016) ✓ ✓  47.40 
System typeSystem nameAnnotated learner dataF0.5
CoNLLLang-8CLC
1.2M11-48M29M
Classif. Susanto, Phandi, and Ng (2014) ✓   35.44 
Rozovskaya and Roth (2016) ✓   43.11 
 
MT Mizumoto and Matsumoto (2016) ✓ ✓  40.00 
Yuan and Briscoe (2016) ✓  ✓ 39.90 
Chollampatt, Taghipour, and Ng (2016) ✓ ✓  41.75 
Hoang, Chollampatt, and Ng (2016) ✓ ✓  41.19 
Rozovskaya and Roth (2016) ✓   28.25 
Rozovskaya and Roth (2016) ✓ ✓  39.48 
Junczys-Dowmunt and Grundkiewicz (2016) ✓ ✓  49.49 
 
Combined Susanto, Phandi, and Ng (2014) ✓ ✓  39.39 
Rozovskaya and Roth (2016) ✓ ✓  47.40 
Close Modal

or Create an Account

Close Modal
Close Modal