nih_exporter.md

NIH ExPORTER Corpus

Sample

name: nih_exporter
fullname: NIH ExPORTER Corpus
lang: en
category: formal
description: NIH ExPORTER
homepage: https://exporter.nih.gov
version: 1.0.0
num_docs: 1017230
num_docs_before_processing: 4046133
num_segments: 1017230
num_sents: 13540126
num_words: 326974102
size_in_bytes: 2255917404
num_bytes_before_processing: 8010604445
size_in_human_bytes: 2.10 GiB
data_files_modified: '2022-02-23 10:24:44'
meta_files_modified: '2022-02-23 10:01:35'
info_updated: '2022-02-26 03:06:09'
data_files:
  train: nih_exporter-train.parquet
meta_files:
  train: meta-nih_exporter-train.parquet
features:
  columns:
    id: id
    text: text
  data:
    id: int
    text: str
  meta:
    id: int
    appl_id: str