dictabert-joint / README.md
Shaltiel's picture
Update README.md
d821a61 verified
|
raw
history blame
10.3 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 joint parsing of the following tasks:

  • Prefix Segmentation
  • Morphological Disabmgiuation
  • Lexicographical Analysis (Lemmatization)
  • Syntactical Parsing (Dependency-Tree)
  • Named-Entity Recognition

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

Sample usage:

from transformers import AutoModel, AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained('dicta-il/dictabert-joint')
model = AutoModel.from_pretrained('dicta-il/dictabert-joint', 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:

[
  {
    "text": "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",
    "tokens": [
      {
        "token": "讘砖谞转",
        "syntax": {
          "word": "讘砖谞转",
          "dep_head_idx": 2,
          "dep_func": "obl",
          "dep_head": "讛砖诇讬诐"
        },
        "seg": [
          "讘",
          "砖谞转"
        ],
        "lex": "砖谞讛",
        "morph": {
          "token": "讘砖谞转",
          "pos": "NOUN",
          "feats": {
            "Gender": "Fem",
            "Number": "Sing"
          },
          "prefixes": [
            "ADP"
          ],
          "suffix": false
        }
      },
      {
        "token": "1948",
        "syntax": {
          "word": "1948",
          "dep_head_idx": 0,
          "dep_func": "compound",
          "dep_head": "讘砖谞转"
        },
        "seg": [
          "1948"
        ],
        "lex": "1948",
        "morph": {
          "token": "1948",
          "pos": "NUM",
          "feats": {},
          "prefixes": [],
          "suffix": false
        }
      },
      {
        "token": "讛砖诇讬诐",
        "syntax": {
          "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"
        },
        "seg": [
          "讛砖诇讬诐"
        ],
        "lex": "讛砖诇讬诐",
        "morph": {
          "token": "讛砖诇讬诐",
          "pos": "VERB",
          "feats": {
            "Gender": "Masc",
            "Number": "Sing",
            "Person": "3",
            "Tense": "Past"
          },
          "prefixes": [],
          "suffix": false
        }
      },
      {
        "token": "讗驻专讬诐",
        "syntax": {
          "word": "讗驻专讬诐",
          "dep_head_idx": 2,
          "dep_func": "nsubj",
          "dep_head": "讛砖诇讬诐"
        },
        "seg": [
          "讗驻专讬诐"
        ],
        "lex": "讗驻专讬诐",
        "morph": {
          "token": "讗驻专讬诐",
          "pos": "PROPN",
          "feats": {},
          "prefixes": [],
          "suffix": false
        }
      },
      {
        "token": "拽讬砖讜谉",
        "syntax": {
          "word": "拽讬砖讜谉",
          "dep_head_idx": 3,
          "dep_func": "flat",
          "dep_head": "讗驻专讬诐"
        },
        "seg": [
          "拽讬砖讜谉"
        ],
        "lex": "拽讬砖讜谉",
        "morph": {
          "token": "拽讬砖讜谉",
          "pos": "PROPN",
          "feats": {},
          "prefixes": [],
          "suffix": false
        }
      },
      {
        "token": "讗转",
        "syntax": {
          "word": "讗转",
          "dep_head_idx": 6,
          "dep_func": "case",
          "dep_head": "诇讬诪讜讚讬讜"
        },
        "seg": [
          "讗转"
        ],
        "lex": "讗转",
        "morph": {
          "token": "讗转",
          "pos": "ADP",
          "feats": {},
          "prefixes": [],
          "suffix": false
        }
      },
      {
        "token": "诇讬诪讜讚讬讜",
        "syntax": {
          "word": "诇讬诪讜讚讬讜",
          "dep_head_idx": 2,
          "dep_func": "obj",
          "dep_head": "讛砖诇讬诐"
        },
        "seg": [
          "诇讬诪讜讚讬讜"
        ],
        "lex": "诇讬诪讜讚",
        "morph": {
          "token": "诇讬诪讜讚讬讜",
          "pos": "NOUN",
          "feats": {
            "Gender": "Masc",
            "Number": "Plur"
          },
          "prefixes": [],
          "suffix": "PRON",
          "suffix_feats": {
            "Gender": "Masc",
            "Number": "Sing",
            "Person": "3"
          }
        }
      },
      {
        "token": "讘驻讬住讜诇",
        "syntax": {
          "word": "讘驻讬住讜诇",
          "dep_head_idx": 6,
          "dep_func": "nmod",
          "dep_head": "诇讬诪讜讚讬讜"
        },
        "seg": [
          "讘",
          "驻讬住讜诇"
        ],
        "lex": "驻讬住讜诇",
        "morph": {
          "token": "讘驻讬住讜诇",
          "pos": "NOUN",
          "feats": {
            "Gender": "Masc",
            "Number": "Sing"
          },
          "prefixes": [
            "ADP"
          ],
          "suffix": false
        }
      },
      {
        "token": "诪转讻转",
        "syntax": {
          "word": "诪转讻转",
          "dep_head_idx": 7,
          "dep_func": "compound",
          "dep_head": "讘驻讬住讜诇"
        },
        "seg": [
          "诪转讻转"
        ],
        "lex": "诪转讻转",
        "morph": {
          "token": "诪转讻转",
          "pos": "NOUN",
          "feats": {
            "Gender": "Fem",
            "Number": "Sing"
          },
          "prefixes": [],
          "suffix": false
        }
      },
      {
        "token": "讜讘转讜诇讚讜转",
        "syntax": {
          "word": "讜讘转讜诇讚讜转",
          "dep_head_idx": 7,
          "dep_func": "conj",
          "dep_head": "讘驻讬住讜诇"
        },
        "seg": [
          "讜讘",
          "转讜诇讚讜转"
        ],
        "lex": "转讜诇讚讛",
        "morph": {
          "token": "讜讘转讜诇讚讜转",
          "pos": "NOUN",
          "feats": {
            "Gender": "Fem",
            "Number": "Plur"
          },
          "prefixes": [
            "CCONJ",
            "ADP"
          ],
          "suffix": false
        }
      },
      {
        "token": "讛讗诪谞讜转",
        "syntax": {
          "word": "讛讗诪谞讜转",
          "dep_head_idx": 9,
          "dep_func": "compound",
          "dep_head": "讜讘转讜诇讚讜转"
        },
        "seg": [
          "讛",
          "讗诪谞讜转"
        ],
        "lex": "讗讜诪谞讜转",
        "morph": {
          "token": "讛讗诪谞讜转",
          "pos": "NOUN",
          "feats": {
            "Gender": "Fem",
            "Number": "Sing"
          },
          "prefixes": [
            "DET"
          ],
          "suffix": false
        }
      },
      {
        "token": "讜讛讞诇",
        "syntax": {
          "word": "讜讛讞诇",
          "dep_head_idx": 2,
          "dep_func": "conj",
          "dep_head": "讛砖诇讬诐"
        },
        "seg": [
          "讜",
          "讛讞诇"
        ],
        "lex": "讛讞诇",
        "morph": {
          "token": "讜讛讞诇",
          "pos": "VERB",
          "feats": {
            "Gender": "Masc",
            "Number": "Sing",
            "Person": "3",
            "Tense": "Past"
          },
          "prefixes": [
            "CCONJ"
          ],
          "suffix": false
        }
      },
      {
        "token": "诇驻专住诐",
        "syntax": {
          "word": "诇驻专住诐",
          "dep_head_idx": 11,
          "dep_func": "xcomp",
          "dep_head": "讜讛讞诇"
        },
        "seg": [
          "诇驻专住诐"
        ],
        "lex": "驻专住诐",
        "morph": {
          "token": "诇驻专住诐",
          "pos": "VERB",
          "feats": {},
          "prefixes": [],
          "suffix": false
        }
      },
      {
        "token": "诪讗诪专讬诐",
        "syntax": {
          "word": "诪讗诪专讬诐",
          "dep_head_idx": 12,
          "dep_func": "obj",
          "dep_head": "诇驻专住诐"
        },
        "seg": [
          "诪讗诪专讬诐"
        ],
        "lex": "诪讗诪专",
        "morph": {
          "token": "诪讗诪专讬诐",
          "pos": "NOUN",
          "feats": {
            "Gender": "Masc",
            "Number": "Plur"
          },
          "prefixes": [],
          "suffix": false
        }
      },
      {
        "token": "讛讜诪讜专讬住讟讬讬诐",
        "syntax": {
          "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"
        },
        "seg": [
          "讛讜诪讜专讬住讟讬讬诐"
        ],
        "lex": "讛讜诪讜专讬住讟讬",
        "morph": {
          "token": "讛讜诪讜专讬住讟讬讬诐",
          "pos": "ADJ",
          "feats": {
            "Gender": "Masc",
            "Number": "Plur"
          },
          "prefixes": [],
          "suffix": false
        }
      }
    ],
    "root_idx": 2,
    "ner_entities": [
      {
        "phrase": "1948",
        "label": "TIMEX"
      },
      {
        "phrase": "讗驻专讬诐 拽讬砖讜谉",
        "label": "PER"
      }
    ]
  }
]

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}
}

License

Shield: CC BY 4.0

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

CC BY 4.0