Pieter Delobelle
commited on
Commit
•
053b9e7
1
Parent(s):
7eba1ca
Update README.md
Browse files
README.md
CHANGED
@@ -15,7 +15,7 @@ datasets:
|
|
15 |
- europarl-mono
|
16 |
- conll2002
|
17 |
widget:
|
18 |
-
- text: "Hallo, ik ben RobBERT, een <mask> taalmodel van de KU Leuven"
|
19 |
---
|
20 |
|
21 |
<p align="center">
|
@@ -41,7 +41,7 @@ and also achieved outstanding, near-sota results for:
|
|
41 |
- [Natural language inference](https://arxiv.org/pdf/2101.05716.pdf)*
|
42 |
- [Review classification](https://medium.com/broadhorizon-cmotions/nlp-with-r-part-5-state-of-the-art-in-nlp-transformers-bert-3449e3cd7494)*
|
43 |
|
44 |
-
|
45 |
|
46 |
*(Also note that this list is not exhaustive. If you used RobBERT for your application, we are happy to know about it! Send us a mail, or add it yourself to this list by sending a pull request with the edit!)*
|
47 |
|
@@ -198,7 +198,7 @@ Replicating our paper experiments is [described in detail on teh RobBERT reposit
|
|
198 |
## Name Origin of RobBERT
|
199 |
|
200 |
Most BERT-like models have the word *BERT* in their name (e.g. [RoBERTa](https://huggingface.co/transformers/model_doc/roberta.html), [ALBERT](https://arxiv.org/abs/1909.11942), [CamemBERT](https://camembert-model.fr/), and [many, many others](https://huggingface.co/models?search=bert)).
|
201 |
-
As such, we queried our newly trained model using its masked language model to name itself
|
202 |
We thought it was really quite fitting, given that RobBERT is a [*very* Dutch name](https://en.wikipedia.org/wiki/Robbert) *(and thus clearly a Dutch language model)*, and additionally has a high similarity to its root architecture, namely [RoBERTa](https://huggingface.co/transformers/model_doc/roberta.html).
|
203 |
|
204 |
Since *"rob"* is a Dutch words to denote a seal, we decided to draw a seal and dress it up like [Bert from Sesame Street](https://muppet.fandom.com/wiki/Bert) for the [RobBERT logo](https://github.com/iPieter/RobBERT/blob/master/res/robbert_logo.png).
|
|
|
15 |
- europarl-mono
|
16 |
- conll2002
|
17 |
widget:
|
18 |
+
- text: "Hallo, ik ben RobBERT, een <mask> taalmodel van de KU Leuven."
|
19 |
---
|
20 |
|
21 |
<p align="center">
|
|
|
41 |
- [Natural language inference](https://arxiv.org/pdf/2101.05716.pdf)*
|
42 |
- [Review classification](https://medium.com/broadhorizon-cmotions/nlp-with-r-part-5-state-of-the-art-in-nlp-transformers-bert-3449e3cd7494)*
|
43 |
|
44 |
+
\\* *Note that several evaluations use RobBERT-v1, and that the second and improved RobBERT-v2 outperforms this first model on everything we tested*
|
45 |
|
46 |
*(Also note that this list is not exhaustive. If you used RobBERT for your application, we are happy to know about it! Send us a mail, or add it yourself to this list by sending a pull request with the edit!)*
|
47 |
|
|
|
198 |
## Name Origin of RobBERT
|
199 |
|
200 |
Most BERT-like models have the word *BERT* in their name (e.g. [RoBERTa](https://huggingface.co/transformers/model_doc/roberta.html), [ALBERT](https://arxiv.org/abs/1909.11942), [CamemBERT](https://camembert-model.fr/), and [many, many others](https://huggingface.co/models?search=bert)).
|
201 |
+
As such, we queried our newly trained model using its masked language model to name itself *\\<mask\\>bert* using [all](https://huggingface.co/pdelobelle/robbert-v2-dutch-base?text=Mijn+naam+is+%3Cmask%3Ebert.) [kinds](https://huggingface.co/pdelobelle/robbert-v2-dutch-base?text=Hallo%2C+ik+ben+%3Cmask%3Ebert.) [of](https://huggingface.co/pdelobelle/robbert-v2-dutch-base?text=Leuk+je+te+ontmoeten%2C+ik+heet+%3Cmask%3Ebert.) [prompts](https://huggingface.co/pdelobelle/robbert-v2-dutch-base?text=Niemand+weet%2C+niemand+weet%2C+dat+ik+%3Cmask%3Ebert+heet.), and it consistently called itself RobBERT.
|
202 |
We thought it was really quite fitting, given that RobBERT is a [*very* Dutch name](https://en.wikipedia.org/wiki/Robbert) *(and thus clearly a Dutch language model)*, and additionally has a high similarity to its root architecture, namely [RoBERTa](https://huggingface.co/transformers/model_doc/roberta.html).
|
203 |
|
204 |
Since *"rob"* is a Dutch words to denote a seal, we decided to draw a seal and dress it up like [Bert from Sesame Street](https://muppet.fandom.com/wiki/Bert) for the [RobBERT logo](https://github.com/iPieter/RobBERT/blob/master/res/robbert_logo.png).
|