config/reference_lists.yaml

english:
  unigrams:
    COCA_magazine_frequency_token:
      display_name: COCA Magazine Frequency (Token)
      description: Frequency and range data from COCA magazine subcorpus - token-based
        analysis
      file: resources/reference_lists/en/COCA_magazine_unigram_list.csv
      format: tsv
      columns: &id001
        word: 0
        frequency: 1
        normalized_freq: 2
        range: 3
        dispersion: 4
      has_header: false
      enabled: true
      analysis_type: token
      log_transformable:
      - frequency
      - normalized_freq
      selectable_measures:
      - frequency
      - normalized_freq
      - range
      - dispersion
      default_measures:
      - frequency
      - normalized_freq
      - range
      default_log_transforms:
      - frequency
      - normalized_freq
      measure_classifications:
        frequency: frequency
        normalized_freq: frequency
        range: range
        dispersion: range

    COCA_magazine_frequency_lemma:
      display_name: COCA Magazine Frequency (Lemma)
      description: Frequency and range data from COCA magazine subcorpus - lemma-based
        analysis
      file: resources/reference_lists/en/COCA_magazine_unigram_list.csv
      format: tsv
      columns: *id001
      has_header: false
      enabled: true
      analysis_type: lemma
      log_transformable:
      - frequency
      - normalized_freq
      selectable_measures:
      - frequency
      - normalized_freq
      - range
      - dispersion
      default_measures:
      - frequency
      - normalized_freq
      - range
      default_log_transforms:
      - frequency
      - normalized_freq
      measure_classifications:
        frequency: frequency
        normalized_freq: frequency
        range: range
        dispersion: range

    COCA_spoken_frequency_token:
      display_name: COCA Spoken Frequency (Token)
      description: Frequency and range data from COCA spoken subcorpus - token-based
        analysis
      file: resources/reference_lists/en/COCA_spoken_unigram_list.csv
      format: tsv
      columns:
        word: 0
        frequency: 1
        normalized_freq: 2
        range: 3
        dispersion: 4
      has_header: false
      enabled: true
      analysis_type: token
      log_transformable:
      - frequency
      - normalized_freq
      selectable_measures:
      - frequency
      - normalized_freq
      - range
      - dispersion
      default_measures:
      - frequency
      - normalized_freq
      default_log_transforms:
      - frequency
      - normalized_freq
      
    COCA_spoken_frequency_lemma:
      display_name: COCA Spoken Frequency (Lemma)
      description: Frequency and range data from COCA spoken subcorpus - lemma-based
        analysis
      file: resources/reference_lists/en/COCA_spoken_unigram_list.csv
      format: tsv
      columns:
        word: 0
        frequency: 1
        normalized_freq: 2
        range: 3
        dispersion: 4
      has_header: false
      enabled: true
      analysis_type: lemma
      log_transformable:
      - frequency
      - normalized_freq
      selectable_measures:
      - frequency
      - normalized_freq
      - range
      - dispersion
      default_measures:
      - frequency
      - normalized_freq
      default_log_transforms:
      - frequency
      - normalized_freq

    # Psycholinguistic norm
    concreteness_ratings_token:
      display_name: Concreteness Ratings (Token)
      description: Concreteness ratings for English words (1-5 scale) - token-based
        analysis
      file: resources/reference_lists/en/Concreteness_Brysbaert.txt
      format: tsv
      columns: &id002
        word: 0
        concreteness: 1
      has_header: true
      enabled: true
      analysis_type: token
      log_transformable: []
      selectable_measures:
      - concreteness
      default_measures:
      - concreteness
      default_log_transforms: []
      measure_classifications:
        concreteness: psycholinguistic
      header_prefix: '#'

    concreteness_ratings_lemma:
      display_name: Concreteness Ratings (Lemma)
      description: Concreteness ratings for English words (1-5 scale) - lemma-based
        analysis
      file: resources/reference_lists/en/Concreteness_Brysbaert.txt
      format: tsv
      columns: *id002
      has_header: true
      enabled: true
      analysis_type: lemma
      log_transformable: []
      selectable_measures:
      - concreteness
      default_measures:
      - concreteness
      default_log_transforms: []
      measure_classifications:
        concreteness: psycholinguistic
      header_prefix: '#'

    aoa_ratings_token:
      display_name: Age of Acquisition (AOA) Ratings (lemma)
      description: Age of Acquisition (AOA) ratings for English words - lemma-based
        analysis
      file: resources/reference_lists/en/AoA_Brysbart.txt
      format: tsv
      columns:
        word: 0
        AOA: 1
      has_header: true
      enabled: true
      analysis_type: lemma
      log_transformable: []
      selectable_measures:
      - AOA
      default_measures:
      - AOA
      default_log_transforms: []
      measure_classifications:
        concreteness: AOA
      header_prefix: '#'

    aoe_ratings_lemma:
      display_name: Age of Exposure (AOE) (Lemma)
      description: Age of Exposure (AOA) based on K-12 textbooks - lemma-based
        analysis
      file: resources/reference_lists/en/AOE_words_dictionary.csv
      format: tsv
      columns: &id018
        word: 0
        InverseAverage: 1
        InverseLinearRegressionSlope: 2
        IndexAboveThreshold40: 3
        InflectionPointPolynomial: 4
      has_header: true
      enabled: true
      analysis_type: lemma
      log_transformable: []
      selectable_measures:
      - InverseAverage
      - InverseLinearRegressionSlope  
      - IndexAboveThreshold40
      - InflectionPointPolynomial
      default_measures:
      - InflectionPointPolynomial
      measure_classifications:
        InverseAverage: psycholinguistic
        InverseLinearRegressionSlope: psycholinguistic
        IndexAboveThreshold40: psycholinguistic
        InflectionPointPolynomial: psycholinguistic
      header_prefix: '#'
      default_log_transforms: []
      measure_classifications:
        InflectionPointPolynomial: AOE
        IndexAboveThreshold40: AOE
      header_prefix: '#'

    semd_token:
      display_name: SemD (Token)
      description: Semantic Diversity (SemD) for English words - token-based
        analysis
      file: resources/reference_lists/en/SemD.txt
      format: tsv
      columns: &id019
        word: 0
        semd: 1
      has_header: true
      enabled: true
      analysis_type: token
      log_transformable: []
      selectable_measures:
      - semd
      default_measures:
      - semd
      default_log_transforms: []
      measure_classifications:
        semd: contextual distinctiveness
      header_prefix: '#'

    mcd_cd_token:
      display_name: McD CD (Token)
      description: Macdonald Contextual Diversity (McD CD) for English words - token-based
        analysis
      file: resources/reference_lists/en/Mcd_CD.txt
      format: tsv
      columns: &id020
        word: 0
        mcd: 1
      has_header: false
      enabled: true
      analysis_type: token
      log_transformable: []
      selectable_measures:
      - mcd
      default_measures:
      - mcd
      measure_classifications:
        mcd: contextual_diversity
      header_prefix: '#'

    academic_words_token:
      display_name: Academic Word List (Token)
      description: Common academic vocabulary for research writing - token-based analysis
      file: resources/reference_lists/en/academic_words_token.csv
      format: csv
      columns: &id003
        word: 0
        frequency: 1
      has_header: true
      enabled: false
      analysis_type: token
      log_transformable:
      - frequency
      selectable_measures:
      - frequency
      default_measures:
      - frequency
      default_log_transforms:
      - frequency
      measure_classifications:
        frequency: frequency

    academic_words_lemma:
      display_name: Academic Word List (Lemma)
      description: Common academic vocabulary for research writing - lemma-based analysis
      file: resources/reference_lists/en/academic_words_lemma.csv
      format: csv
      columns: *id003
      has_header: true
      enabled: false
      analysis_type: lemma
      log_transformable:
      - frequency
      selectable_measures:
      - frequency
      default_measures:
      - frequency
      default_log_transforms:
      - frequency
      measure_classifications:
        frequency: frequency

  bigrams:
    COCA_spoken_bigram_frequency_token:
      display_name: COCA Spoken Bigram Frequency (Token)
      description: Bigram frequencies and range data - token-based analysis
      file: resources/reference_lists/en/COCA_spoken_bigram_list.csv
      format: tsv
      columns: &id004
        bigram: 0
        frequency: 1
        normalized_freq: 2
        documents: 3
        range: 4
      has_header: false
      enabled: true
      analysis_type: token
      log_transformable:
      - frequency
      - normalized_freq
      selectable_measures:
      - frequency
      - normalized_freq
      - documents
      - range
      default_measures:
      - frequency
      - normalized_freq
      - range
      default_log_transforms:
      - frequency
      - normalized_freq
      measure_classifications:
        frequency: frequency
        normalized_freq: frequency
        documents: range
        range: range

    COCA_spoken_bigram_frequency_lemma:
      display_name: COCA Spoken Bigram Frequency (Lemma)
      description: Bigram frequencies and range data - lemma-based analysis
      file: resources/reference_lists/en/COCA_spoken_bigram_list.csv
      format: tsv
      columns: *id004
      has_header: false
      enabled: true
      analysis_type: lemma
      log_transformable:
      - frequency
      - normalized_freq
      selectable_measures:
      - frequency
      - normalized_freq
      - documents
      - range
      default_measures:
      - frequency
      - normalized_freq
      - range
      default_log_transforms:
      - frequency
      - normalized_freq
      measure_classifications:
        frequency: frequency
        normalized_freq: frequency
        documents: range
        range: range

    COCA_spoken_bigram_association_token:
      display_name: COCA Spoken Bigram Associations (Token)
      description: Bigram association measures (MI, T-score, Delta P) - token-based
        analysis
      file: resources/reference_lists/en/spoken_bi_contingency.csv
      format: csv
      columns: &id005
        bigram: 0
        frequency: 1
        mi_score: 2
        mi_2_score: 3
        t_score: 4
        delta_p: 5
        ap_collex: 6
      has_header: true
      enabled: true
      analysis_type: token
      log_transformable:
      - frequency
      selectable_measures:
      - frequency
      - mi_score
      - mi_2_score
      - t_score
      - delta_p
      - ap_collex
      default_measures:
      - frequency
      - t_score
      default_log_transforms:
      - frequency
      measure_classifications:
        frequency: frequency
        mi_score: association
        mi_2_score: association
        t_score: association
        delta_p: association
        ap_collex: association

    COCA_spoken_bigram_association_lemma:
      display_name: COCA Spoken Bigram Associations (Lemma)
      description: Bigram association measures (MI, T-score, Delta P) - lemma-based
        analysis
      file: resources/reference_lists/en/spoken_bigram_lemma_contingency.csv
      format: csv
      columns: &id021
        bigram: 0
        frequency: 1
        mi_score: 5
        mi_2_score: 6
        t_score: 7
        delta_p: 8
        ap_collex: 9        
      has_header: true
      enabled: true
      analysis_type: lemma
      log_transformable:
      - frequency
      selectable_measures:
      - frequency
      - mi_score
      - mi_2_score
      - t_score
      - delta_p
      - ap_collex
      default_measures:
      - frequency
      - t_score
      default_log_transforms:
      - frequency
      measure_classifications:
        frequency: frequency
        mi_score: association
        mi_2_score: association
        t_score: association
        delta_p: association
        ap_collex: association

    COCA_magazine_bigram_frequency_token:
      display_name: COCA Magazine Bigram Frequency (Token)
      description: Bigram frequencies and range data in Magazine - token-based analysis
      file: resources/reference_lists/en/COCA_magazine_bigram_list.csv
      format: tsv
      columns: &id006
        bigram: 0
        frequency: 1
        normalized_freq: 2
        documents: 3
        range: 4
      has_header: false
      enabled: true
      analysis_type: token
      log_transformable:
      - frequency
      - normalized_freq
      selectable_measures:
      - frequency
      - normalized_freq
      - documents
      - range
      default_measures:
      - frequency
      - normalized_freq
      - range
      default_log_transforms:
      - frequency
      - normalized_freq
      measure_classifications:
        frequency: frequency
        normalized_freq: frequency
        documents: range
        range: range

    COCA_magazine_bigram_frequency_lemma:
      display_name: COCA Magazine Bigram Frequency (Lemma)
      description: Bigram frequencies and range data in Magazine - lemma-based analysis
      file: resources/reference_lists/en/COCA_spoken_bigram_list.csv
      format: tsv
      columns: *id006
      has_header: false
      enabled: true
      analysis_type: lemma
      log_transformable:
      - frequency
      - normalized_freq
      selectable_measures:
      - frequency
      - normalized_freq
      - documents
      - range
      default_measures:
      - frequency
      - normalized_freq
      - range
      default_log_transforms:
      - frequency
      - normalized_freq
      measure_classifications:
        frequency: frequency
        normalized_freq: frequency
        documents: range
        range: range

    COCA_magazine_bigram_association_token:
      display_name: COCA Magazine Bigram Associations (Token)
      description: Bigram association measures (MI, T-score, Delta P) - token-based
        analysis
      file: resources/reference_lists/en/magazine_bi_contingency.csv
      format: csv
      columns: &id007
        bigram: 0
        frequency: 1
        mi_score: 2
        mi_2_score: 3
        t_score: 4
        delta_p: 5
        ap_collex: 6
      has_header: true
      enabled: true
      analysis_type: token
      log_transformable:
      - frequency
      selectable_measures:
      - frequency
      - mi_score
      - mi_2_score
      - t_score
      - delta_p
      - ap_collex
      default_measures:
      - frequency
      - t_score
      default_log_transforms:
      - frequency
      measure_classifications:
        frequency: frequency
        mi_score: association
        mi_2_score: association
        t_score: association
        delta_p: association
        ap_collex: association
    COCA_magazine_bigram_association_lemma:
      display_name: COCA Magazine Bigram Associations (Lemma)
      description: Bigram association measures (MI, T-score, Delta P) - lemma-based
        analysis
      file: resources/reference_lists/en/magazine_bigram_lemma_contingency.csv
      format: csv
      columns: *id007
      has_header: true
      enabled: false
      analysis_type: lemma
      log_transformable:
      - frequency
      selectable_measures:
      - frequency
      - mi_score
      - mi_2_score
      - t_score
      - delta_p
      - ap_collex
      default_measures:
      - frequency
      - t_score
      default_log_transforms:
      - frequency
      measure_classifications:
        frequency: frequency
        mi_score: association
        mi_2_score: association
        t_score: association
        delta_p: association
        ap_collex: association
  trigrams:
    COCA_trigram_frequency_token:
      display_name: COCA Trigram Frequency (Token)
      description: Trigram frequencies and range data - token-based analysis
      file: resources/reference_lists/en/COCA_spoken_trigram_list.csv
      format: tsv
      columns: &id008
        trigram: 0
        frequency: 1
        normalized_freq: 2
        range: 3
        dispersion: 4
      has_header: false
      enabled: true
      analysis_type: token
      log_transformable:
      - frequency
      - normalized_freq
      selectable_measures:
      - frequency
      - normalized_freq
      - range
      - dispersion
      default_measures:
      - frequency
      - normalized_freq
      - range
      default_log_transforms:
      - frequency
      - normalized_freq
      measure_classifications:
        frequency: frequency
        normalized_freq: frequency
        range: range
        dispersion: range
    COCA_trigram_frequency_lemma:
      display_name: COCA Trigram Frequency (Lemma)
      description: Trigram frequencies and range data - lemma-based analysis
      file: resources/reference_lists/en/COCA_spoken_trigram_list.csv
      format: tsv
      columns: *id008
      has_header: false
      enabled: true
      analysis_type: lemma
      log_transformable:
      - frequency
      - normalized_freq
      selectable_measures:
      - frequency
      - normalized_freq
      - range
      - dispersion
      default_measures:
      - frequency
      - normalized_freq
      - range
      default_log_transforms:
      - frequency
      - normalized_freq
      measure_classifications:
        frequency: frequency
        normalized_freq: frequency
        range: range
        dispersion: range
    COCA_trigram_assoc_uni_bi_token:
      display_name: COCA Trigram→Bigram Associations (Token)
      description: Trigram to bigram association measures - token-based analysis
      file: resources/reference_lists/en/spoken_tri_contingency_1.csv
      format: csv
      columns: &id009
        trigram: 0
        frequency: 1
        mi_score: 2
        mi_2_score: 3
        t_score: 4
        delta_p: 5
        ap_collex: 6
      has_header: true
      enabled: true
      analysis_type: token
      log_transformable:
      - frequency
      selectable_measures:
      - frequency
      - mi_score
      - mi_2_score
      - t_score
      - delta_p
      - ap_collex
      default_measures:
      - frequency
      - t_score
      default_log_transforms:
      - frequency
      measure_classifications:
        frequency: frequency
        mi_score: association
        mi_2_score: association
        t_score: association
        delta_p: association
        ap_collex: association
    COCA_trigram_assoc_uni_bi_lemma:
      display_name: COCA Trigram→Bigram Associations (Lemma)
      description: Trigram to bigram association measures - lemma-based analysis
      file: resources/reference_lists/en/spoken_trigram_lemma_contingency_1.csv
      format: csv
      columns: *id009
      has_header: true
      enabled: false
      analysis_type: lemma
      log_transformable:
      - frequency
      selectable_measures:
      - frequency
      - mi_score
      - mi_2_score
      - t_score
      - delta_p
      - ap_collex
      default_measures:
      - frequency
      - t_score
      default_log_transforms:
      - frequency
      measure_classifications:
        frequency: frequency
        mi_score: association
        mi_2_score: association
        t_score: association
        delta_p: association
        ap_collex: association
    COCA_trigram_assoc_bi_uni_token:
      display_name: COCA Trigram→Unigram Associations (Token)
      description: Trigram to unigram association measures - token-based analysis
      file: resources/reference_lists/en/spoken_tri_contingency_2.csv
      format: csv
      columns: &id010
        trigram: 0
        frequency: 1
        mi_score: 2
        mi_2_score: 3
        t_score: 4
        delta_p: 5
        ap_collex: 6
      has_header: true
      enabled: true
      analysis_type: token
      log_transformable:
      - frequency
      selectable_measures:
      - frequency
      - mi_score
      - mi_2_score
      - t_score
      - delta_p
      - ap_collex
      default_measures:
      - frequency
      - t_score
      default_log_transforms:
      - frequency
      measure_classifications:
        frequency: frequency
        mi_score: association
        mi_2_score: association
        t_score: association
        delta_p: association
        ap_collex: association
    COCA_trigram_assoc_bi_uni_lemma:
      display_name: COCA Trigram→Unigram Associations (Lemma)
      description: Trigram to unigram association measures - lemma-based analysis
      file: resources/reference_lists/en/spoken_trigram_lemma_contingency_2.csv
      format: csv
      columns: *id010
      has_header: true
      enabled: false
      analysis_type: lemma
      log_transformable:
      - frequency
      selectable_measures:
      - frequency
      - mi_score
      - mi_2_score
      - t_score
      - delta_p
      - ap_collex
      default_measures:
      - frequency
      - t_score
      default_log_transforms:
      - frequency
      measure_classifications:
        frequency: frequency
        mi_score: association
        mi_2_score: association
        t_score: association
        delta_p: association
        ap_collex: association
japanese:
  unigrams:
    BCCWJ_frequency_token:
      display_name: BCCWJ Written - Frequency (Token)
      description: BCCWJ raw frequency counts for written Japanese - token-based analysis
      file: resources/reference_lists/ja/BCCWJ_frequencylist_suw_ver1_1.tsv
      format: tsv
      columns: &id011
        surface_form: 1
        lemma: 2
        pos: 3
        frequency: 6
      has_header: true
      enabled: true
      analysis_type: token
      log_transformable:
      - frequency
      selectable_measures:
      - pos
      - frequency
      default_measures:
      - frequency
      - pos
      default_log_transforms:
      - frequency
      measure_classifications:
        pos: unknown
        frequency: frequency
      japanese_corpus: true
    BCCWJ_frequency_lemma:
      display_name: BCCWJ Written - Frequency (Lemma)
      description: BCCWJ raw frequency counts for written Japanese - lemma-based analysis
      file: resources/reference_lists/ja/BCCWJ_frequencylist_suw_ver1_1.tsv
      format: tsv
      columns: *id011
      has_header: true
      enabled: true
      analysis_type: lemma
      log_transformable:
      - frequency
      selectable_measures:
      - pos
      - frequency
      default_measures:
      - frequency
      - pos
      default_log_transforms:
      - frequency
      measure_classifications:
        pos: unknown
        frequency: frequency
      japanese_corpus: true
    BCCWJ_pmw_token:
      display_name: BCCWJ Written - Per Million Words (Token)
      description: BCCWJ normalized frequency for written Japanese - token-based analysis
      file: resources/reference_lists/ja/BCCWJ_frequencylist_suw_ver1_1.tsv
      format: tsv
      columns: &id012
        surface_form: 1
        lemma: 2
        pos: 3
        frequency: 7
      has_header: true
      enabled: true
      analysis_type: token
      log_transformable:
      - frequency
      selectable_measures:
      - pos
      - frequency
      default_measures:
      - frequency
      - pos
      default_log_transforms:
      - frequency
      measure_classifications:
        pos: unknown
        frequency: frequency
      japanese_corpus: true
    BCCWJ_pmw_lemma:
      display_name: BCCWJ Written - Per Million Words (Lemma)
      description: BCCWJ normalized frequency for written Japanese - lemma-based analysis
      file: resources/reference_lists/ja/BCCWJ_frequencylist_suw_ver1_1.tsv
      format: tsv
      columns: *id012
      has_header: true
      enabled: true
      analysis_type: lemma
      log_transformable:
      - frequency
      selectable_measures:
      - pos
      - frequency
      default_measures:
      - frequency
      - pos
      default_log_transforms:
      - frequency
      measure_classifications:
        pos: unknown
        frequency: frequency
      japanese_corpus: true
    BCCWJ_rank_token:
      display_name: BCCWJ Written - Frequency Rank (Token)
      description: BCCWJ frequency ranking for written Japanese - token-based analysis
      file: resources/reference_lists/ja/BCCWJ_frequencylist_suw_ver1_1.tsv
      format: tsv
      columns: &id013
        surface_form: 1
        lemma: 2
        pos: 3
        frequency: 0
      has_header: true
      enabled: true
      analysis_type: token
      log_transformable:
      - frequency
      selectable_measures:
      - pos
      - frequency
      default_measures:
      - frequency
      - pos
      default_log_transforms:
      - frequency
      measure_classifications:
        pos: unknown
        frequency: frequency
      japanese_corpus: true
    BCCWJ_rank_lemma:
      display_name: BCCWJ Written - Frequency Rank (Lemma)
      description: BCCWJ frequency ranking for written Japanese - lemma-based analysis
      file: resources/reference_lists/ja/BCCWJ_frequencylist_suw_ver1_1.tsv
      format: tsv
      columns: *id013
      has_header: true
      enabled: true
      analysis_type: lemma
      log_transformable:
      - frequency
      selectable_measures:
      - pos
      - frequency
      default_measures:
      - frequency
      - pos
      default_log_transforms:
      - frequency
      measure_classifications:
        pos: unknown
        frequency: frequency
      japanese_corpus: true
    CSJ_frequency_token:
      display_name: CSJ Spoken - Frequency (Token)
      description: CSJ raw frequency counts for spoken Japanese - token-based analysis
      file: resources/reference_lists/ja/CSJ_frequencylist_suw_ver201803.tsv
      format: tsv
      columns: &id014
        surface_form: 1
        lemma: 2
        pos: 3
        frequency: 6
      has_header: true
      enabled: true
      analysis_type: token
      log_transformable:
      - frequency
      selectable_measures:
      - pos
      - frequency
      default_measures:
      - frequency
      - pos
      default_log_transforms:
      - frequency
      measure_classifications:
        pos: unknown
        frequency: frequency
      japanese_corpus: true
    CSJ_frequency_lemma:
      display_name: CSJ Spoken - Frequency (Lemma)
      description: CSJ raw frequency counts for spoken Japanese - lemma-based analysis
      file: resources/reference_lists/ja/CSJ_frequencylist_suw_ver201803.tsv
      format: tsv
      columns: *id014
      has_header: true
      enabled: true
      analysis_type: lemma
      log_transformable:
      - frequency
      selectable_measures:
      - pos
      - frequency
      default_measures:
      - frequency
      - pos
      default_log_transforms:
      - frequency
      measure_classifications:
        pos: unknown
        frequency: frequency
      japanese_corpus: true
    CSJ_pmw_token:
      display_name: CSJ Spoken - Per Million Words (Token)
      description: CSJ normalized frequency for spoken Japanese - token-based analysis
      file: resources/reference_lists/ja/CSJ_frequencylist_suw_ver201803.tsv
      format: tsv
      columns: &id015
        surface_form: 1
        lemma: 2
        pos: 3
        frequency: 7
      has_header: true
      enabled: true
      analysis_type: token
      log_transformable:
      - frequency
      selectable_measures:
      - pos
      - frequency
      default_measures:
      - frequency
      - pos
      default_log_transforms:
      - frequency
      measure_classifications:
        pos: unknown
        frequency: frequency
      japanese_corpus: true
    CSJ_pmw_lemma:
      display_name: CSJ Spoken - Per Million Words (Lemma)
      description: CSJ normalized frequency for spoken Japanese - lemma-based analysis
      file: resources/reference_lists/ja/CSJ_frequencylist_suw_ver201803.tsv
      format: tsv
      columns: *id015
      has_header: true
      enabled: true
      analysis_type: lemma
      log_transformable:
      - frequency
      selectable_measures:
      - pos
      - frequency
      default_measures:
      - frequency
      - pos
      default_log_transforms:
      - frequency
      measure_classifications:
        pos: unknown
        frequency: frequency
      japanese_corpus: true
    CSJ_rank_token:
      display_name: CSJ Spoken - Frequency Rank (Token)
      description: CSJ frequency ranking for spoken Japanese - token-based analysis
      file: resources/reference_lists/ja/CSJ_frequencylist_suw_ver201803.tsv
      format: tsv
      columns: &id016
        surface_form: 1
        lemma: 2
        pos: 3
        frequency: 0
      has_header: true
      enabled: true
      analysis_type: token
      log_transformable:
      - frequency
      selectable_measures:
      - pos
      - frequency
      default_measures:
      - frequency
      - pos
      default_log_transforms:
      - frequency
      measure_classifications:
        pos: unknown
        frequency: frequency
      japanese_corpus: true
    CSJ_rank_lemma:
      display_name: CSJ Spoken - Frequency Rank (Lemma)
      description: CSJ frequency ranking for spoken Japanese - lemma-based analysis
      file: resources/reference_lists/ja/CSJ_frequencylist_suw_ver201803.tsv
      format: tsv
      columns: *id016
      has_header: true
      enabled: true
      analysis_type: lemma
      log_transformable:
      - frequency
      selectable_measures:
      - pos
      - frequency
      default_measures:
      - frequency
      - pos
      default_log_transforms:
      - frequency
      measure_classifications:
        pos: unknown
        frequency: frequency
      japanese_corpus: true
      
    jp_frequency_token:
      display_name: Japanese Frequency List (Token)
      description: Frequency data for Japanese words - token-based analysis
      file: resources/reference_lists/ja/jp_frequency_token.csv
      format: csv
      columns: &id017
        word: 0
        frequency: 1
      has_header: true
      enabled: false
      analysis_type: token
      log_transformable:
      - frequency
      selectable_measures:
      - frequency
      default_measures:
      - frequency
      default_log_transforms:
      - frequency
      measure_classifications:
        frequency: frequency

    jp_frequency_lemma:
      display_name: Japanese Frequency List (Lemma)
      description: Frequency data for Japanese words - lemma-based analysis
      file: resources/reference_lists/ja/jp_frequency_lemma.csv
      format: csv
      columns: *id017
      has_header: true
      enabled: false
      analysis_type: lemma
      log_transformable:
      - frequency
      selectable_measures:
      - frequency
      default_measures:
      - frequency
      default_log_transforms:
      - frequency
      measure_classifications:
        frequency: frequency