CAS-SIAT-XinHai/ManiTable

---
license: mit
configs:
- config_name: HiTab
data_files:
- split: train
path: HiTab/train-*
- split: validation
path: HiTab/validation-*
- split: test
path: HiTab/test-*
- config_name: ManiTable-HTML
data_files:
- split: train
path: ManiTable-HTML/train-*
- split: test
path: ManiTable-HTML/test-*
- config_name: ManiTable-MD
data_files:
- split: train
path: ManiTable-MD/train-*
- split: test
path: ManiTable-MD/test-*
- config_name: MultiHiertt
data_files:
- split: train
path: MultiHiertt/train-*
- split: validation
path: MultiHiertt/validation-*
- split: test
path: MultiHiertt/test-*
- config_name: ToTTo
data_files:
- split: train
path: ToTTo/train-*
- split: validation
path: ToTTo/validation-*
- split: test
path: ToTTo/test-*
dataset_info:
- config_name: HiTab
features:
- name: id
dtype: string
- name: table_id
dtype: string
- name: table_source
dtype: string
- name: sentence_id
dtype: string
- name: sub_sentence_id
dtype: string
- name: sub_sentence
dtype: string
- name: question
dtype: string
- name: answer
dtype: string
- name: aggregation
dtype: string
- name: linked_cells
dtype: string
- name: answer_formulas
dtype: string
- name: reference_cells_map
dtype: string
- name: table_html
dtype: string
- name: table_texts
list:
list: string
- name: table_hmt
dtype: string
splits:
- name: train
num_bytes: 91120526
num_examples: 7417
- name: validation
num_bytes: 20829800
num_examples: 1671
- name: test
num_bytes: 19184583
num_examples: 1584
download_size: 12416229
dataset_size: 131134909
- config_name: ManiTable-HTML
features:
- name: id
dtype: string
- name: source
dtype: string
- name: task
dtype: string
- name: prompt
dtype: string
- name: target
dtype: string
- name: response
dtype: string
splits:
- name: train
num_bytes: 482452
num_examples: 60
- name: test
num_bytes: 3704350
num_examples: 900
download_size: 778899
dataset_size: 4186802
- config_name: ManiTable-MD
features:
- name: id
dtype: string
- name: task
dtype: string
- name: source
dtype: string
- name: target
dtype: string
- name: prompt
dtype: string
- name: response_interleaved_thinking
dtype: string
- name: response_thinking
dtype: string
splits:
- name: train
num_bytes: 6559103
num_examples: 1076
- name: test
num_bytes: 1067769
num_examples: 600
download_size: 3093803
dataset_size: 7626872
- config_name: MultiHiertt
features:
- name: uid
dtype: string
- name: paragraphs
list: string
- name: tables
list: string
- name: table_description
dtype: string
- name: qa
struct:
- name: answer
dtype: string
- name: program
dtype: string
- name: question
dtype: string
- name: question_type
dtype: string
- name: table_evidence
list: string
- name: text_evidence
list: int64
splits:
- name: train
num_bytes: 238362649
num_examples: 7830
- name: validation
num_bytes: 32882106
num_examples: 1044
- name: test
num_bytes: 47836007
num_examples: 1566
download_size: 95680700
dataset_size: 319080762
- config_name: ToTTo
features:
- name: table
list:
list:
- name: column_span
dtype: int64
- name: is_header
dtype: bool
- name: row_span
dtype: int64
- name: value
dtype: string
- name: table_webpage_url
dtype: string
- name: table_page_title
dtype: string
- name: table_section_title
dtype: string
- name: table_section_text
dtype: string
- name: highlighted_cells
list:
list: int64
- name: example_id
dtype: int64
- name: sentence_annotations
list:
- name: final_sentence
dtype: string
- name: original_sentence
dtype: string
- name: sentence_after_ambiguity
dtype: string
- name: sentence_after_deletion
dtype: string
- name: overlap_subset
dtype: bool
- name: table_html
dtype: string
splits:
- name: train
num_bytes: 2086543576
num_examples: 120761
- name: validation
num_bytes: 139437648
num_examples: 7700
- name: test
num_bytes: 136836495
num_examples: 7700
download_size: 542435946
dataset_size: 2362817719
---