32 lines
1.5 KiB
Markdown
32 lines
1.5 KiB
Markdown
|
---
|
||
|
|
language: ja
|
||
|
|
license: cc-by-4.0
|
||
|
|
library_name: sentence-transformers
|
||
|
|
tags:
|
||
|
|
- xlm-roberta
|
||
|
|
- nli
|
||
|
|
datasets:
|
||
|
|
- jnli
|
||
|
|
- jsick
|
||
|
|
---
|
||
|
|
|
||
|
|
# Japanese Natural Language Inference Model
|
||
|
|
This model was trained using [SentenceTransformers](https://sbert.net) [Cross-Encoder](https://www.sbert.net/examples/applications/cross-encoder/README.html) class, [gradient accumulation PR](https://github.com/UKPLab/sentence-transformers/pull/1092), and the code from [CyberAgentAILab/japanese-nli-model](https://github.com/CyberAgentAILab/japanese-nli-model).
|
||
|
|
|
||
|
|
## Training Data
|
||
|
|
The model was trained on the [JGLUE-JNLI](https://github.com/yahoojapan/JGLUE) and [JSICK](https://github.com/verypluming/JSICK) datasets. For a given sentence pair, it will output three scores corresponding to the labels: contradiction, entailment, neutral.
|
||
|
|
|
||
|
|
## Usage
|
||
|
|
```python
|
||
|
|
from transformers import AutoTokenizer, AutoModelForSequenceClassification
|
||
|
|
tokenizer = AutoTokenizer.from_pretrained('cyberagent/xlm-roberta-large-jnli-jsick')
|
||
|
|
model = AutoModelForSequenceClassification.from_pretrained('cyberagent/xlm-roberta-large-jnli-jsick')
|
||
|
|
features = tokenizer(["子供が走っている猫を見ている", "猫が走っている"], ["猫が走っている", "子供が走っている"], padding=True, truncation=True, return_tensors="pt")
|
||
|
|
model.eval()
|
||
|
|
with torch.no_grad():
|
||
|
|
scores = model(**features).logits
|
||
|
|
label_mapping = ['contradiction', 'entailment', 'neutral']
|
||
|
|
labels = [label_mapping[score_max] for score_max in scores.argmax(dim=1)]
|
||
|
|
print(labels)
|
||
|
|
```
|