Class: Datasets::NagoyaUniversityConversationCorpus

Inherits:
Dataset
  • Object
show all
Defined in:
lib/datasets/nagoya-university-conversation-corpus.rb

Defined Under Namespace

Classes: Data, Participant, Sentence

Instance Attribute Summary

Attributes inherited from Dataset

#metadata

Instance Method Summary collapse

Methods inherited from Dataset

#clear_cache!, #to_table

Constructor Details

#initialize ⇒ NagoyaUniversityConversationCorpus

Returns a new instance of NagoyaUniversityConversationCorpus.



29
30
31
32
33
34
35
36
37
38
39
40
 
# File 'lib/datasets/nagoya-university-conversation-corpus.rb', line 29

def initialize
  super()
  @metadata.id = 'nagoya-university-conversation-curpus'
  @metadata.name = 'Nagoya University Conversation Curpus'
  @metadata.url = 'https://mmsrv.ninjal.ac.jp/nucc/'
  @metadata.licenses = ['CC-BY-NC-ND-4.0']
  @metadata.description = <<~DESCRIPTION
    The "Nagoya University Conversation Corpus" is a corpus of 129 conversations,
    total about 100 hours of chatting among native speakers of Japanese,
    which is converted into text.
  DESCRIPTION
end

Instance Method Details

#each ⇒ Object 



42
43
44
45
46
47
48
 
# File 'lib/datasets/nagoya-university-conversation-corpus.rb', line 42

def each
  return to_enum(__method__) unless block_given?

  open_data do |input_stream|
    yield(parse_file(input_stream))
  end
end