gyorilab/bioner_evaluation_corpora

---
dataset_info:
- config_name: bc2gm
features:
- name: id
dtype: string
- name: text
dtype: string
- name: entities
struct:
- name: start
list: int32
- name: end
list: int32
- name: label
list:
class_label:
names:
'0': GENE
- name: text
list: string
splits:
- name: train
num_bytes: 2815829
num_examples: 12500
- name: validation
num_bytes: 561582
num_examples: 2500
- name: test
num_bytes: 1134304
num_examples: 5000
download_size: 3036644
dataset_size: 4511715
- config_name: biored
features:
- name: id
dtype: string
- name: pmid
dtype: string
- name: passage_type
dtype: string
- name: text
dtype: string
- name: entities
struct:
- name: start
list: int32
- name: end
list: int32
- name: label
list:
class_label:
names:
'0': CellLine
'1': ChemicalEntity
'2': DiseaseOrPhenotypicFeature
'3': GeneOrGeneProduct
'4': OrganismTaxon
'5': SequenceVariant
- name: text
list: string
splits:
- name: train
num_bytes: 1103907
num_examples: 800
- name: validation
num_bytes: 290516
num_examples: 200
- name: test
num_bytes: 284572
num_examples: 200
download_size: 1199442
dataset_size: 1678995
- config_name: tmvar
features:
- name: id
dtype: string
- name: pmid
dtype: string
- name: passage_type
dtype: string
- name: text
dtype: string
- name: entities
struct:
- name: start
list: int32
- name: end
list: int32
- name: label
list:
class_label:
names:
'0': AcidChange
'1': CellLine
'2': DNAAllele
'3': DNAMutation
'4': Gene
'5': OtherMutation
'6': ProteinAllele
'7': ProteinMutation
'8': SNP
'9': Species
- name: text
list: string
splits:
- name: test
num_bytes: 1097886
num_examples: 1000
download_size: 682394
dataset_size: 1097886
configs:
- config_name: bc2gm
data_files:
- split: train
path: bc2gm/train-*
- split: validation
path: bc2gm/validation-*
- split: test
path: bc2gm/test-*
- config_name: biored
data_files:
- split: train
path: biored/train-*
- split: validation
path: biored/validation-*
- split: test
path: biored/test-*
- config_name: tmvar
data_files:
- split: test
path: tmvar/test-*
---