gaetangate commited on
Commit
dbef85d
1 Parent(s): d1b9887

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -28,11 +28,11 @@ license: cc-by-nc-sa-4.0
28
 
29
  # KnowGL: Knowledge Generation and Linking from Text
30
 
31
- The `knowgl-large` model [Rossiello et al. (AAAI 2023)](https://arxiv.org/pdf/2210.13952.pdf) is trained by combining Wikidata with an extended version of the training data [REBEL](https://huggingface.co/datasets/Babelscape/rebel-dataset) dataset. Given a sentence, it generates triple(s) in the following format -
32
  ```
33
  [(subject mention # subject label # subject type) | relation label | (object mention # object label # object type)]
34
  ```
35
- If there is more than one triple generated, they are separated by `$` in the output.
36
 
37
  The model achieves state-of-the-art results for relation extraction on the REBEL dataset. See results in [Mihindukulasooriya et al. (ISWC 2022)](https://arxiv.org/pdf/2207.05188.pdf).
38
 
 
28
 
29
  # KnowGL: Knowledge Generation and Linking from Text
30
 
31
+ The `knowgl-large` model is trained by combining Wikidata with an extended version of the training data [REBEL](https://huggingface.co/datasets/Babelscape/rebel-dataset) dataset. Given a sentence, KnowGL generates triple(s) in the following format:
32
  ```
33
  [(subject mention # subject label # subject type) | relation label | (object mention # object label # object type)]
34
  ```
35
+ If there is more than one triple generated, they are separated by `$` in the output. More details in [Rossiello et al. (AAAI 2023)](https://arxiv.org/pdf/2210.13952.pdf).
36
 
37
  The model achieves state-of-the-art results for relation extraction on the REBEL dataset. See results in [Mihindukulasooriya et al. (ISWC 2022)](https://arxiv.org/pdf/2207.05188.pdf).
38