Create dataset indonesian_chat_data

- uid: indonesian_chat_data
- type: primary
- description:
- name: Indonesian Chat data
- description: Indonesian corpora for chat summarization.
- homepage: https://aclanthology.org/L16-1129.pdf
- validated: True
- languages:
- language_names:
- Indonesian
- language_comments: Colloquial
- language_locations:
- South-eastern Asia
- Indonesia
- validated: False
- custodian:
- name: Fajri Koto
- in_catalogue:
- type: A private individual
- location: Indonesia
- contact_name: Fajri Koto
- contact_email: Fajri.fajri@samsung.com
- contact_submitter: True
- additional: http://www.fajrikoto.com/
- validated: False
- availability:
- procurement:
- for_download: No - we would need to spontaneously reach out to the current owners/custodians
- download_url:
- download_email: Fajri.fajri@samsung.com
- licensing:
- has_licenses: Unclear
- license_text: Since this data collection is done while the creator is in the private company, it might be difficult.
- license_properties:
- license_list:
- pii:
- has_pii: Unclear
- generic_pii_likely:
- generic_pii_list:
- numeric_pii_likely:
- numeric_pii_list:
- sensitive_pii_likely:
- sensitive_pii_list:
- no_pii_justification_class: general knowledge not written by or referring to private persons
- no_pii_justification_text:
- validated: False
- source_category:
- category_type: collection
- category_web:
- category_media: Chats
- validated: False
- media:
- category:
- text
- image
- text_format:
- other
- Unclear
- audiovisual_format:
- image_format:
- other
- Unclear
- database_format:
- text_is_transcribed: No
- instance_type: Chat sentence
- instance_count: n<100
- instance_size: n<10
- validated: False
- fname: indonesian_chat_data.json