Name
Abstract | ||
|---|---|---|
This paper presents a mixed deterministic model for coreference resolution in the CoNLL-2012 shared task. We separate the two main stages of our model, mention detection and coreference resolution, into several sub-tasks which are solved by machine learning method and deterministic rules based on multi-filters, such as lexical, syntactic, semantic, gender and number information. We participate in the closed track for English and Chinese, and also submit an open result for Chinese using tools to generate the required features. Finally, we reach the average F1 scores 58.68, 60.69 and 61.02 on the English closed task, Chinese closed and open tasks. |
Year | Venue | Keywords |
|---|---|---|
2012 | EMNLP-CoNLL Shared Task | open task,f1 score,deterministic rule,coreference resolution,closed track,main stage,number information,conll-2012 shared task,open result,mixed deterministic model |
Field | DocType | Volume |
Coreference,Computer science,Artificial intelligence,Natural language processing,Deterministic system,Syntax,Machine learning | Conference | W12-45 |
Citations | PageRank | References |
5 | 0.46 | 9 |
Authors | ||
8 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Bo Yuan | 1 | 5 | 0.46 |
| Qingcai Chen | 2 | 809 | 66.72 |
| Yang Xiang | 3 | 5 | 0.46 |
| Xiaolong Wang | 4 | 1208 | 115.39 |
| Liping Ge | 5 | 5 | 0.46 |
| Zengjian Liu | 6 | 35 | 3.84 |
| Meng Liao | 7 | 5 | 0.46 |
| Xianbo Si | 8 | 5 | 0.46 |