Update README.md
Browse files
README.md
CHANGED
|
@@ -1,7 +1,13 @@
|
|
| 1 |
rebel-base-chinese-cndbpedia is a generation-based relation extraction model
|
|
|
|
| 2 |
·a SOTA chinese end-to-end relation extraction model.
|
|
|
|
| 3 |
·using the training method of "REBEL：Relation Extraction By End-to-end Language generation"(EMNLP Findings 2021).
|
|
|
|
| 4 |
·using the Distant-supervised data from cndbpedia.
|
|
|
|
| 5 |
·can perform SOTA in many chinese relation extraction dataset,such as lic2019,lic2020,HacRED,etc.
|
|
|
|
| 6 |
·easy to use,just like normal generation task.
|
|
|
|
| 7 |
·input is sentence,and output is linearlize triples,such as input:姚明是一名NBA篮球运动员 output:[subj]姚明[obj]NBA[rel]公司[obj]篮球运动员[rel]职业(more details can read on REBEL paper)
|
|
|
|
| 1 |
rebel-base-chinese-cndbpedia is a generation-based relation extraction model
|
| 2 |
+
|
| 3 |
·a SOTA chinese end-to-end relation extraction model.
|
| 4 |
+
|
| 5 |
·using the training method of "REBEL：Relation Extraction By End-to-end Language generation"(EMNLP Findings 2021).
|
| 6 |
+
|
| 7 |
·using the Distant-supervised data from cndbpedia.
|
| 8 |
+
|
| 9 |
·can perform SOTA in many chinese relation extraction dataset,such as lic2019,lic2020,HacRED,etc.
|
| 10 |
+
|
| 11 |
·easy to use,just like normal generation task.
|
| 12 |
+
|
| 13 |
·input is sentence,and output is linearlize triples,such as input:姚明是一名NBA篮球运动员 output:[subj]姚明[obj]NBA[rel]公司[obj]篮球运动员[rel]职业(more details can read on REBEL paper)
|