Name
Title | ||
|---|---|---|
Chinese Grammatical Error Diagnosis using Statistical and Prior Knowledge driven Features with Probabilistic Ensemble Enhancement. |
Abstract | ||
|---|---|---|
This paper describes our system at NLPTEA-2018 Task #1: Chinese Grammatical Error Diagnosis. Grammatical Error Diagnosis is one of the most challenging NLP tasks, which is to locate grammar errors and tell error types. Our system is built on the model of bidirectional Long Short-Term Memory with a conditional random field layer (BiLSTM-CRF) but integrates with several new features. First, richer features are considered in the BiLSTM-CRF model; second, a probabilistic ensemble approach is adopted; third, Template Matcher are used during a post-processing to bring in human knowledge. In official evaluation, our system obtains the highest F-1 scores at identifying error types and locating error positions, the second highest F-1 score at sentence level error detection. We also recommend error corrections for specific error types and achieve the best F1 performance among all participants. |
Year | Venue | Field |
|---|---|---|
2018 | NATURAL LANGUAGE PROCESSING TECHNIQUES FOR EDUCATIONAL APPLICATIONS | Computer science,Natural language processing,Artificial intelligence,Probabilistic logic,Machine learning |
DocType | Citations | PageRank |
Conference | 0 | 0.34 |
References | Authors | |
0 | 9 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Ruiji Fu | 1 | 36 | 4.84 |
| Zhengqi Pei | 2 | 0 | 0.34 |
| Jiefu Gong | 3 | 0 | 0.34 |
| Wei Song | 4 | 32 | 9.95 |
| Dechuan Teng | 5 | 0 | 0.34 |
| Wanxiang Che | 6 | 711 | 66.39 |
| Shijin Wang | 7 | 180 | 31.56 |
| Guoping Hu | 8 | 18 | 2.06 |
| Ting Liu | 9 | 2735 | 232.31 |