first model version

.gitignore

@@ -0,0 +1,2 @@
+.DS_Store
+.idea/

README.md

@@ -1,7 +1,21 @@
+---
+language:
+- en
+  tags:
+- NER
+- named entity recognition
+- RE
+- relation extraction
+- entity mention detection
+- EMD
+- coreference resolution
+  license: apache-2.0
+  datasets:
+- Ontonotes
+- CoNLL04
+---
+
 # CoReNer
 
 A multi-task model for named-entity recognition, relation extraction, entity mention detection and coreference resolution. 
-See details and usage examples at: https://github.com/aiola-lab/corener
-
----
-license: apache-2.0
+See details and usage examples at: https://github.com/aiola-lab/corener.

config.json

@@ -0,0 +1,149 @@
+{
+  "_name_or_path": "roberta-base",
+  "architectures": [
+    "RobertaForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "corener_config": {
+    "cls_token": 0,
+    "max_pairs": 1000,
+    "ner_classes": 19,
+    "pad_token": 1,
+    "relation_classes": 5,
+    "size_embedding": 25
+  },
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.19.1",
+  "type_vocab_size": 1,
+  "types": {
+    "entities": {
+      "CARDINAL": {
+        "short": "CARDINAL",
+        "verbose": "CARDINAL"
+      },
+      "DATE": {
+        "short": "DATE",
+        "verbose": "DATE"
+      },
+      "EVENT": {
+        "short": "EVENT",
+        "verbose": "EVENT"
+      },
+      "FAC": {
+        "short": "FAC",
+        "verbose": "Buildings, airports, highways, bridges"
+      },
+      "GPE": {
+        "short": "GPE",
+        "verbose": "Countries, cities, states."
+      },
+      "LANGUAGE": {
+        "short": "LANGUAGE",
+        "verbose": "LANGUAGE"
+      },
+      "LAW": {
+        "short": "LAW",
+        "verbose": "LAW"
+      },
+      "LOC": {
+        "short": "LOC",
+        "verbose": "LOCATION"
+      },
+      "MONEY": {
+        "short": "MONEY",
+        "verbose": "MONEY"
+      },
+      "NORP": {
+        "short": "NORP",
+        "verbose": "Nationalities or religious or political groups"
+      },
+      "ORDINAL": {
+        "short": "ORDINAL",
+        "verbose": "ORDINAL"
+      },
+      "ORG": {
+        "short": "ORG",
+        "verbose": "ORGANIZATION"
+      },
+      "PERCENT": {
+        "short": "PERCENT",
+        "verbose": "PERCENT"
+      },
+      "PERSON": {
+        "short": "PER",
+        "verbose": "PERSON"
+      },
+      "PRODUCT": {
+        "short": "PROD",
+        "verbose": "PRODUCT"
+      },
+      "QUANTITY": {
+        "short": "QUANTITY",
+        "verbose": "QUANTITY"
+      },
+      "TIME": {
+        "short": "TIME",
+        "verbose": "TIME"
+      },
+      "WORK_OF_ART": {
+        "short": "WORK_OF_ART",
+        "verbose": "WORK_OF_ART"
+      }
+    },
+    "mentions": {
+      "MENTION": {
+        "short": "MENTION",
+        "verbose": "MENTION"
+      }
+    },
+    "references": {
+      "COREF": {
+        "short": "COREF",
+        "verbose": "COREF"
+      }
+    },
+    "relations": {
+      "Kill": {
+        "short": "Kill",
+        "symmetric": false,
+        "verbose": "Kill"
+      },
+      "Live_In": {
+        "short": "Live",
+        "symmetric": false,
+        "verbose": "Live in"
+      },
+      "Located_In": {
+        "short": "LocIn",
+        "symmetric": false,
+        "verbose": "Located in"
+      },
+      "OrgBased_In": {
+        "short": "OrgBI",
+        "symmetric": false,
+        "verbose": "Organization based in"
+      },
+      "Work_For": {
+        "short": "Work",
+        "symmetric": false,
+        "verbose": "Work for"
+      }
+    }
+  },
+  "use_cache": true,
+  "vocab_size": 50265
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3bab81b34f26b5dedf4a0a9ecd5090883ecf1e6fcd61fb88f48264f406e5196
+size 525207305

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "do_lower_case": false, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "roberta-base", "tokenizer_class": "RobertaTokenizer"}