tlemberger commited on
Commit
a0eface
1 Parent(s): 9281402

reverting to dataset sd-nlp

Browse files
Files changed (1) hide show
  1. README.md +5 -5
README.md CHANGED
@@ -6,7 +6,7 @@ tags:
6
  - token classification
7
  license: agpl-3.0
8
  datasets:
9
- - EMBO/sd-panels
10
  metrics:
11
  -
12
  ---
@@ -15,7 +15,7 @@ metrics:
15
 
16
  ## Model description
17
 
18
- This model is a [RoBERTa base model](https://huggingface.co/roberta-base) that was further trained using a masked language modeling task on a compendium of English scientific textual examples from the life sciences using the [BioLang dataset](https://huggingface.co/datasets/EMBO/biolang). It was then fine-tuned for token classification on the SourceData [sd-panels](https://huggingface.co/datasets/EMBO/sd-panels) dataset with the `GENEPROD_ROLES` configuration to perform pure context-dependent semantic role classification of bioentities.
19
 
20
 
21
  ## Intended uses & limitations
@@ -30,7 +30,7 @@ To have a quick check of the model:
30
  from transformers import pipeline, RobertaTokenizerFast, RobertaForTokenClassification
31
  example = """<s>The <mask> overexpression in cells caused an increase in <mask> expression.</s>"""
32
  tokenizer = RobertaTokenizerFast.from_pretrained('roberta-base', max_len=512)
33
- model = RobertaForTokenClassification.from_pretrained('EMBO/sd-roles')
34
  ner = pipeline('ner', model, tokenizer=tokenizer)
35
  res = ner(example)
36
  for r in res:
@@ -43,7 +43,7 @@ The model must be used with the `roberta-base` tokenizer.
43
 
44
  ## Training data
45
 
46
- The model was trained for token classification using the [EMBO/sd-panels dataset](https://huggingface.co/datasets/EMBO/sd-panels) which includes manually annotated examples.
47
 
48
  ## Training procedure
49
 
@@ -53,7 +53,7 @@ Training code is available at https://github.com/source-data/soda-roberta
53
 
54
  - Model fine-tuned: EMBL/bio-lm
55
  - Tokenizer vocab size: 50265
56
- - Training data: EMBO/sd-panels
57
  - Dataset configuration: GENEPROD_ROLES
58
  - Training with 48771 examples.
59
  - Evaluating on 13801 examples.
 
6
  - token classification
7
  license: agpl-3.0
8
  datasets:
9
+ - EMBO/sd-nlp
10
  metrics:
11
  -
12
  ---
 
15
 
16
  ## Model description
17
 
18
+ This model is a [RoBERTa base model](https://huggingface.co/roberta-base) that was further trained using a masked language modeling task on a compendium of English scientific textual examples from the life sciences using the [BioLang dataset](https://huggingface.co/datasets/EMBO/biolang). It was then fine-tuned for token classification on the SourceData [sd-nlp](https://huggingface.co/datasets/EMBO/sd-nlp) dataset with the `GENEPROD_ROLES` configuration to perform pure context-dependent semantic role classification of bioentities.
19
 
20
 
21
  ## Intended uses & limitations
 
30
  from transformers import pipeline, RobertaTokenizerFast, RobertaForTokenClassification
31
  example = """<s>The <mask> overexpression in cells caused an increase in <mask> expression.</s>"""
32
  tokenizer = RobertaTokenizerFast.from_pretrained('roberta-base', max_len=512)
33
+ model = RobertaForTokenClassification.from_pretrained('EMBO/sd-geneprod-roles')
34
  ner = pipeline('ner', model, tokenizer=tokenizer)
35
  res = ner(example)
36
  for r in res:
 
43
 
44
  ## Training data
45
 
46
+ The model was trained for token classification using the [EMBO/sd-nlp dataset](https://huggingface.co/datasets/EMBO/sd-nlp) which includes manually annotated examples.
47
 
48
  ## Training procedure
49
 
 
53
 
54
  - Model fine-tuned: EMBL/bio-lm
55
  - Tokenizer vocab size: 50265
56
+ - Training data: EMBO/sd-nlp
57
  - Dataset configuration: GENEPROD_ROLES
58
  - Training with 48771 examples.
59
  - Evaluating on 13801 examples.