ICT2214Team7/GPT_Generated_Dataset_Fold4_2000

---
dataset_info:
features:
- name: id
dtype: string
- name: tokens
sequence: string
- name: pos_tags
sequence:
class_label:
names:
'0': '"'
'1': ''''''
'2': '#'
'3': $
'4': (
'5': )
'6': ','
'7': .
'8': ':'
'9': '``'
'10': CC
'11': CD
'12': DT
'13': EX
'14': FW
'15': IN
'16': JJ
'17': JJR
'18': JJS
'19': LS
'20': MD
'21': NN
'22': NNP
'23': NNPS
'24': NNS
'25': NN|SYM
'26': PDT
'27': POS
'28': PRP
'29': PRP$
'30': RB
'31': RBR
'32': RBS
'33': RP
'34': SYM
'35': TO
'36': UH
'37': VB
'38': VBD
'39': VBG
'40': VBN
'41': VBP
'42': VBZ
'43': WDT
'44': WP
'45': WP$
'46': WRB
- name: chunk_tags
sequence:
class_label:
names:
'0': O
'1': B-ADJP
'2': I-ADJP
'3': B-ADVP
'4': I-ADVP
'5': B-CONJP
'6': I-CONJP
'7': B-INTJ
'8': I-INTJ
'9': B-LST
'10': I-LST
'11': B-NP
'12': I-NP
'13': B-PP
'14': I-PP
'15': B-PRT
'16': I-PRT
'17': B-SBAR
'18': I-SBAR
'19': B-UCP
'20': I-UCP
'21': B-VP
'22': I-VP
'23': B-PNP
'24': I-PNP
- name: ner_tags
sequence:
class_label:
names:
'0': O
'1': B-PER
'2': I-PER
'3': B-ORG
'4': I-ORG
'5': B-LOC
'6': I-LOC
'7': B-MISC
'8': I-MISC
'9': B-NAT
'10': I-NAT
'11': B-AGE
'12': I-AGE
splits:
- name: train
num_bytes: 2232682
num_examples: 1280
- name: validation
num_bytes: 591413
num_examples: 320
- name: test
num_bytes: 712771
num_examples: 400
download_size: 482501
dataset_size: 3536866
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
- split: validation
path: data/validation-*
- split: test
path: data/test-*
---