Init commit.

LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) Microsoft Corporation
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
+IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
+DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
+OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE
+OR OTHER DEALINGS IN THE SOFTWARE.

README.md

@@ -1,3 +1,31 @@
 ---
+language: en
+tags:
+- exbert
 license: mit
+pipeline_tag: sentence-similarity
+widget:
+- text: "We aimed to find drug targets using the 2DE / <ENT> MS </ENT> proteomics study of a dexamethasone - resistant cell line."
 ---
+
+## KRISSBERT
+
+Entity linking faces significant challenges such as prolific variations and prevalent ambiguities, especially in high-value domains with myriad entities. Standard classification approaches suffer from the annotation bottleneck and cannot effectively handle unseen entities. Zero-shot entity linking has emerged as a promising direction for generalizing to new entities, but it still requires example gold entity mentions during training and canonical descriptions for all entities, both of which are rarely available outside of Wikipedia ([Logeswaran et al., 2019](https://aclanthology.org/P19-1335.pdf); [Wu et al., 2020](https://aclanthology.org/2020.emnlp-main.519.pdf)). We explore Knowledge-RIch Self-Supervision (KRISS) and train a contextual encoder (KRISSBERT) for entity linking, by leveraging readily available unlabeled text and domain knowledge.
+
+This KRISSBERT is initialized with [PubMedBERT](https://huggingface.co/microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract) parameters, and then trained using self-supervised examples that are generated by combining [PubMed](https://pubmed.ncbi.nlm.nih.gov/) abstracts and the [UMLS](https://www.nlm.nih.gov/research/umls/index.html) ontology. Experiments on seven standard biomedical entity linking datasets show that KRISSBERT attains new state of the art, outperforming prior self-supervised methods by as much as 20 absolute points in accuracy.
+See [Zhang et al., 2021](https://arxiv.org/abs/2112.07887) for the details.
+
+## Citation
+
+If you find KRISSBERT useful in your research, please cite the following paper:
+
+```latex
+@article{krissbert,
+  author = {Sheng Zhang, Hao Cheng, Shikhar Vashishth, Cliff Wong, Jinfeng Xiao, Xiaodong Liu, Tristan Naumann, Jianfeng Gao, Hoifung Poon},
+  title = {Knowledge-Rich Self-Supervised Entity Linking},
+  year = {2021},
+  url = {https://arxiv.org/abs/2112.07887},
+  eprinttype = {arXiv},
+  eprint = {2112.07887},
+}
+```

added_tokens.json

@@ -0,0 +1 @@
+{"<ENT>": 30522, "</ENT>": 30523, "[DUMMY]": 30524}

config.json

@@ -0,0 +1,20 @@
+{
+  "architectures": [
+    "KRISSBERT"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "type_vocab_size": 2,
+  "vocab_size": 30525
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef3e691fc051582e2e4dd84d521b197afee5b39e7990095a7d27db709be10356
+size 438012339

special_tokens_map.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": true, "special_tokens_map_file": null, "full_tokenizer_file": null}