Hugging Face's logo

dicta-il
/
dictabert-syntax

Feature Extraction
Transformers
PyTorch
Safetensors
Hebrew
bert
custom_code
text-embeddings-inference
Model card Files Community
dictabert-syntax / README.md
Shaltiel's picture
Shaltiel
Update README.md
d23c5a4 verified
preview code
|
raw
history blame
4.31 kB
metadata
license: cc-by-4.0
language:
  - he
inference: false

DictaBERT: A State-of-the-Art BERT Suite for Modern Hebrew

State-of-the-art language model for Hebrew, released here.

This is the fine-tuned model for the syntax dependency tree parsing task.

For the bert-base models for other tasks, see here.

Sample usage:

from transformers import AutoModel, AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained('dicta-il/dictabert-syntax')
model = AutoModel.from_pretrained('dicta-il/dictabert-syntax', trust_remote_code=True)

model.eval()

sentence = '讘砖谞转 1948 讛砖诇讬诐 讗驻专讬诐 拽讬砖讜谉 讗转 诇讬诪讜讚讬讜 讘驻讬住讜诇 诪转讻转 讜讘转讜诇讚讜转 讛讗诪谞讜转 讜讛讞诇 诇驻专住诐 诪讗诪专讬诐 讛讜诪讜专讬住讟讬讬诐'
print(model.predict([sentence], tokenizer))

Output:

[
  {
    "tree": [
      {
        "word": "讘砖谞转",
        "dep_head_idx": 2,
        "dep_func": "obl",
        "dep_head": "讛砖诇讬诐"
      },
      {
        "word": "1948",
        "dep_head_idx": 0,
        "dep_func": "compound",
        "dep_head": "讘砖谞转"
      },
      {
        "word": "讛砖诇讬诐",
        "dep_head_idx": -1,
        "dep_func": "root",
        "dep_head": "讛讜诪讜专讬住讟讬讬诐"
      },
      {
        "word": "讗驻专讬诐",
        "dep_head_idx": 2,
        "dep_func": "nsubj",
        "dep_head": "讛砖诇讬诐"
      },
      {
        "word": "拽讬砖讜谉",
        "dep_head_idx": 3,
        "dep_func": "flat",
        "dep_head": "讗驻专讬诐"
      },
      {
        "word": "讗转",
        "dep_head_idx": 6,
        "dep_func": "case",
        "dep_head": "诇讬诪讜讚讬讜"
      },
      {
        "word": "诇讬诪讜讚讬讜",
        "dep_head_idx": 2,
        "dep_func": "obj",
        "dep_head": "讛砖诇讬诐"
      },
      {
        "word": "讘驻讬住讜诇",
        "dep_head_idx": 6,
        "dep_func": "nmod",
        "dep_head": "诇讬诪讜讚讬讜"
      },
      {
        "word": "诪转讻转",
        "dep_head_idx": 7,
        "dep_func": "compound",
        "dep_head": "讘驻讬住讜诇"
      },
      {
        "word": "讜讘转讜诇讚讜转",
        "dep_head_idx": 7,
        "dep_func": "conj",
        "dep_head": "讘驻讬住讜诇"
      },
      {
        "word": "讛讗诪谞讜转",
        "dep_head_idx": 9,
        "dep_func": "compound",
        "dep_head": "讜讘转讜诇讚讜转"
      },
      {
        "word": "讜讛讞诇",
        "dep_head_idx": 2,
        "dep_func": "conj",
        "dep_head": "讛砖诇讬诐"
      },
      {
        "word": "诇驻专住诐",
        "dep_head_idx": 11,
        "dep_func": "xcomp",
        "dep_head": "讜讛讞诇"
      },
      {
        "word": "诪讗诪专讬诐",
        "dep_head_idx": 12,
        "dep_func": "obj",
        "dep_head": "诇驻专住诐"
      },
      {
        "word": "讛讜诪讜专讬住讟讬讬诐",
        "dep_head_idx": 13,
        "dep_func": "amod",
        "dep_head": "诪讗诪专讬诐"
      }
    ],
    "root_idx": 2
  }
]

Citation

If you use DictaBERT in your research, please cite DictaBERT: A State-of-the-Art BERT Suite for Modern Hebrew

BibTeX:

@misc{shmidman2023dictabert,
      title={DictaBERT: A State-of-the-Art BERT Suite for Modern Hebrew}, 
      author={Shaltiel Shmidman and Avi Shmidman and Moshe Koppel},
      year={2023},
      eprint={2308.16687},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}

Citation

If you use DictaBERT-syntax in your research, please cite MRL Parsing without Tears: The Case of Hebrew

BibTeX:

@misc{shmidman2024mrl,
      title={MRL Parsing Without Tears: The Case of Hebrew}, 
      author={Shaltiel Shmidman and Avi Shmidman and Moshe Koppel and Reut Tsarfaty},
      year={2024},
      eprint={2403.06970},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}

License

Shield: CC BY 4.0

This work is licensed under a Creative Commons Attribution 4.0 International License.

CC BY 4.0