Update README.md

README.md

@@ -1,3 +1,441 @@
 ---
 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](https://arxiv.org/abs/2308.16687).
+
+This is the fine-tuned BERT-tiny 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](https://huggingface.co/collections/dicta-il/dictabert-6588e7cc08f83845fc42a18b).
+
+Sample usage:
+
+```python
+from transformers import AutoModel, AutoTokenizer
+
+tokenizer = AutoTokenizer.from_pretrained('dicta-il/dictabert-tiny-joint')
+model = AutoModel.from_pretrained('dicta-il/dictabert-tiny-joint', trust_remote_code=True)
+
+model.eval()
+
+sentence = 'בשנת 1948 השלים אפרים קישון את לימודיו בפיסול מתכת ובתולדות האמנות והחל לפרסם מאמרים הומוריסטיים'
+print(model.predict([sentence], tokenizer))
+```
+
+Output:
+```json
+[
+  {
+    "text": "בשנת 1948 השלים אפרים קישון את לימודיו בפיסול מתכת ובתולדות האמנות והחל לפרסם מאמרים הומוריסטיים",
+    "tokens": [
+      {
+        "token": "בשנת",
+        "syntax": {
+          "word": "בשנת",
+          "dep_head_idx": 2,
+          "dep_func": "obl",
+          "dep_head": "השלים"
+        },
+        "seg": [
+          "ב",
+          "שנת"
+        ],
+        "lex": "שנה",
+        "morph": {
+          "token": "בשנת",
+          "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": "בשנת"
+        },
+        "seg": [
+          "1948"
+        ],
+        "lex": "1948",
+        "morph": {
+          "token": "1948",
+          "pos": "NUM",
+          "feats": {},
+          "prefixes": [],
+          "suffix": false
+        }
+      },
+      {
+        "token": "השלים",
+        "syntax": {
+          "word": "השלים",
+          "dep_head_idx": -1,
+          "dep_func": "root",
+          "dep_head": "הומוריסטיים"
+        },
+        "seg": [
+          "השלים"
+        ],
+        "lex": "השלים",
+        "morph": {
+          "token": "השלים",
+          "pos": "VERB",
+          "feats": {
+            "Gender": "Masc",
+            "Number": "Sing",
+            "Person": "3",
+            "Tense": "Past"
+          },
+          "prefixes": [],
+          "suffix": false
+        }
+      },
+      {
+        "token": "אפרים",
+        "syntax": {
+          "word": "אפרים",
+          "dep_head_idx": 2,
+          "dep_func": "nsubj",
+          "dep_head": "השלים"
+        },
+        "seg": [
+          "אפרים"
+        ],
+        "lex": "אפרים",
+        "morph": {
+          "token": "אפרים",
+          "pos": "PROPN",
+          "feats": {},
+          "prefixes": [],
+          "suffix": false
+        }
+      },
+      {
+        "token": "קישון",
+        "syntax": {
+          "word": "קישון",
+          "dep_head_idx": 3,
+          "dep_func": "flat",
+          "dep_head": "אפרים"
+        },
+        "seg": [
+          "קישון"
+        ],
+        "lex": "קישון",
+        "morph": {
+          "token": "קישון",
+          "pos": "PROPN",
+          "feats": {},
+          "prefixes": [],
+          "suffix": false
+        }
+      },
+      {
+        "token": "את",
+        "syntax": {
+          "word": "את",
+          "dep_head_idx": 6,
+          "dep_func": "case",
+          "dep_head": "לימודיו"
+        },
+        "seg": [
+          "את"
+        ],
+        "lex": "את",
+        "morph": {
+          "token": "את",
+          "pos": "ADP",
+          "feats": {},
+          "prefixes": [],
+          "suffix": false
+        }
+      },
+      {
+        "token": "לימודיו",
+        "syntax": {
+          "word": "לימודיו",
+          "dep_head_idx": 2,
+          "dep_func": "obj",
+          "dep_head": "השלים"
+        },
+        "seg": [
+          "לימודיו"
+        ],
+        "lex": "לימוד",
+        "morph": {
+          "token": "לימודיו",
+          "pos": "NOUN",
+          "feats": {
+            "Gender": "Masc",
+            "Number": "Plur"
+          },
+          "prefixes": [],
+          "suffix": "PRON",
+          "suffix_feats": {
+            "Gender": "Masc",
+            "Number": "Sing",
+            "Person": "3"
+          }
+        }
+      },
+      {
+        "token": "בפיסול",
+        "syntax": {
+          "word": "בפיסול",
+          "dep_head_idx": 6,
+          "dep_func": "nmod",
+          "dep_head": "לימודיו"
+        },
+        "seg": [
+          "ב",
+          "פיסול"
+        ],
+        "lex": "פיסול",
+        "morph": {
+          "token": "בפיסול",
+          "pos": "NOUN",
+          "feats": {
+            "Gender": "Masc",
+            "Number": "Sing"
+          },
+          "prefixes": [
+            "ADP"
+          ],
+          "suffix": false
+        }
+      },
+      {
+        "token": "מתכת",
+        "syntax": {
+          "word": "מתכת",
+          "dep_head_idx": 7,
+          "dep_func": "compound",
+          "dep_head": "בפיסול"
+        },
+        "seg": [
+          "מתכת"
+        ],
+        "lex": "מתכת",
+        "morph": {
+          "token": "מתכת",
+          "pos": "NOUN",
+          "feats": {
+            "Gender": "Fem",
+            "Number": "Sing"
+          },
+          "prefixes": [],
+          "suffix": false
+        }
+      },
+      {
+        "token": "ובתולדות",
+        "syntax": {
+          "word": "ובתולדות",
+          "dep_head_idx": 7,
+          "dep_func": "conj",
+          "dep_head": "בפיסול"
+        },
+        "seg": [
+          "וב",
+          "תולדות"
+        ],
+        "lex": "תולדה",
+        "morph": {
+          "token": "ובתולדות",
+          "pos": "NOUN",
+          "feats": {
+            "Gender": "Fem",
+            "Number": "Plur"
+          },
+          "prefixes": [
+            "CCONJ",
+            "ADP"
+          ],
+          "suffix": false
+        }
+      },
+      {
+        "token": "האמנות",
+        "syntax": {
+          "word": "האמנות",
+          "dep_head_idx": 9,
+          "dep_func": "compound",
+          "dep_head": "ובתולדות"
+        },
+        "seg": [
+          "ה",
+          "אמנות"
+        ],
+        "lex": "אומנות",
+        "morph": {
+          "token": "האמנות",
+          "pos": "NOUN",
+          "feats": {
+            "Gender": "Fem",
+            "Number": "Sing"
+          },
+          "prefixes": [
+            "DET"
+          ],
+          "suffix": false
+        }
+      },
+      {
+        "token": "והחל",
+        "syntax": {
+          "word": "והחל",
+          "dep_head_idx": 2,
+          "dep_func": "conj",
+          "dep_head": "השלים"
+        },
+        "seg": [
+          "ו",
+          "החל"
+        ],
+        "lex": "החל",
+        "morph": {
+          "token": "והחל",
+          "pos": "VERB",
+          "feats": {
+            "Gender": "Masc",
+            "Number": "Sing",
+            "Person": "3",
+            "Tense": "Past"
+          },
+          "prefixes": [
+            "CCONJ"
+          ],
+          "suffix": false
+        }
+      },
+      {
+        "token": "לפרסם",
+        "syntax": {
+          "word": "לפרסם",
+          "dep_head_idx": 11,
+          "dep_func": "xcomp",
+          "dep_head": "והחל"
+        },
+        "seg": [
+          "לפרסם"
+        ],
+        "lex": "פרסם",
+        "morph": {
+          "token": "לפרסם",
+          "pos": "VERB",
+          "feats": {},
+          "prefixes": [],
+          "suffix": false
+        }
+      },
+      {
+        "token": "מאמרים",
+        "syntax": {
+          "word": "מאמרים",
+          "dep_head_idx": 12,
+          "dep_func": "obj",
+          "dep_head": "לפרסם"
+        },
+        "seg": [
+          "מאמרים"
+        ],
+        "lex": "מאמר",
+        "morph": {
+          "token": "מאמרים",
+          "pos": "NOUN",
+          "feats": {
+            "Gender": "Masc",
+            "Number": "Plur"
+          },
+          "prefixes": [],
+          "suffix": false
+        }
+      },
+      {
+        "token": "הומוריסטיים",
+        "syntax": {
+          "word": "הומוריסטיים",
+          "dep_head_idx": 13,
+          "dep_func": "amod",
+          "dep_head": "מאמרים"
+        },
+        "seg": [
+          "הומוריסטיים"
+        ],
+        "lex": "הומוריסטי",
+        "morph": {
+          "token": "הומוריסטיים",
+          "pos": "ADJ",
+          "feats": {
+            "Gender": "Masc",
+            "Number": "Plur"
+          },
+          "prefixes": [],
+          "suffix": false
+        }
+      }
+    ],
+    "root_idx": 2,
+    "ner_entities": [
+      {
+        "phrase": "1948",
+        "label": "TIMEX"
+      },
+      {
+        "phrase": "אפרים קישון",
+        "label": "PER"
+      }
+    ]
+  }
+]
+```
+
+
+## Citation
+
+If you use DictaBERT in your research, please cite ```DictaBERT: A State-of-the-Art BERT Suite for Modern Hebrew```
+
+**BibTeX:**
+
+```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][cc-by-shield]][cc-by]
+
+This work is licensed under a
+[Creative Commons Attribution 4.0 International License][cc-by].
+
+[![CC BY 4.0][cc-by-image]][cc-by]
+
+[cc-by]: http://creativecommons.org/licenses/by/4.0/
+[cc-by-image]: https://i.creativecommons.org/l/by/4.0/88x31.png
+[cc-by-shield]: https://img.shields.io/badge/License-CC%20BY%204.0-lightgrey.svg