aihub_patent1.md

AIHub Patent Entire Summary

Sample

name: aihub_patent1
fullname: AIHub Patent Entire Summary
lang: ko
category: paper
description: AIHub/논문자료 요약/특허전체
license: Attribution-NonCommercial (CC-By-NC v3)
homepage: https://aihub.or.kr
version: 1.0.0
num_docs: 155939
num_docs_before_processing: 156300
num_segments: 831278
num_sents: 29206198
num_words: 673134598
size_in_bytes: 6867742099
num_bytes_before_processing: 6909280087
size_in_human_bytes: 6.40 GiB
data_files_modified: '2022-02-21 13:16:05'
meta_files_modified: '2022-02-21 13:02:53'
info_updated: '2022-02-26 03:06:08'
data_files:
  train: aihub_patent1-train.parquet
  test: aihub_patent1-test.parquet
meta_files:
  train: meta-aihub_patent1-train.parquet
  test: meta-aihub_patent1-test.parquet
features:
  columns:
    id: id
    text: text
  data:
    id: int
    text: str
  meta:
    id: int
    split: str
    doc_type: str
    doc_id: str
    title: str
    date: str
    reg_no: str
    ipc: str