Index

A

abbrev_firstname_match() (in module src.aggregation) ABBREVIATION_FILE (src.preprocessing.preprocess.PreprocessConfig attribute) ABBREVIATION_LIST (src.preprocessing.preprocess.PreprocessConfig attribute) ADD_FUZZY_SEARCH (utility.settings.Settings attribute) add_info_to_entity() (in module src.postprocess) add_info_to_place_entity() (in module src.postprocess)

add_sentences() (in module src.tag_flair) adjust_information() (in module src.postprocess) aggregate_names() (in module src.aggregation) aggregate_place() (in module src.aggregation) aggregate_places() (in module src.aggregation) aggregate_with() (in module src.aggregation)

B

backend_api_call() (in module src.linking)

base_url (utility.settings.ElasticSettings attribute) BATCH_SIZE (utility.settings.Settings attribute)

C

check_and_create() (utility.evaluation_utils.Paths method) check_for_abbrev() (in module src.preprocessing.preprocess) check_for_missing_pages() (in module utility.split_year) check_gpu() (in module utility.utils) check_roman_numeral() (in module src.preprocessing.preprocess) clean_lastname() (in module src.aggregation) clean_namestring() (in module utility.linking_utils) clean_raw() (in module utility.evaluation_utils) clean_up_aggregation() (in module src.aggregation) clean_up_aggregation_places() (in module src.aggregation) CLIENT_ID (utility.settings.Settings attribute) CLIENT_SECRET (utility.settings.Settings attribute) compare_gnd_info() (in module utility.compare) compare_linking() (in module utility.compare) compare_linking_person() (in module utility.compare) compare_linking_places() (in module utility.compare)

compare_pagenames() (in module utility.split_year) compare_references() (in module utility.compare) compare_tagging() (in module utility.compare) compare_to_target_ids_multiplexed() (in module src.linking) compare_vector_to_text_ids_multiplexed() (in module src.linking) compute_scores() (utility.evaluation_utils.Scores method) convert_dates_wikidata() (in module utility.linking_utils) convert_gnd_format_kibana() (in module utility.linking_utils) convert_wikidata_format_kibana() (in module utility.linking_utils) create_new_aggregated_place() (in module src.aggregation) create_new_aggregated_unit() (in module src.aggregation) CUSTOM_PATHS (utility.settings.Settings attribute) CUSTOM_TAG_PATH (utility.settings.Settings attribute) CustomSentence (class in src.tag_flair) CustomToken (class in src.tag_flair) cut_pagenumbers() (in module utility.split_year)

D

DATA2_MNT (utility.settings.Settings attribute) decide_articles() (in module src.postprocess)

decide_candidates() (in module src.aggregation) decide_tag_no_tag_lower_prio() (in module src.tag_flair)

E

ElasticSettings (class in utility.settings) EMBEDDINGS_ENDPOINT (utility.settings.Settings attribute) erara_xml_to_word_coord() (in module utility.utils) es (utility.settings.Settings attribute) eval_entity() (in module utility.evaluation_utils) eval_entity_inkb() (in module utility.evaluation_utils) eval_references() (in module utility.evaluation_utils) eval_references_inkb() (in module utility.evaluation_utils)

EVAL_TOPK (utility.settings.Settings attribute) evaluate_person() (in module utility.evaluation_utils) execute_aggregation() (in module src.aggregation) execute_evaluation() (in module src.evaluation) execute_linking() (in module src.linking) execute_postprocessing() (in module src.postprocess) execute_preprocessing() (in module src.preprocessing.preprocess) execute_tagging() (in module src.tag_flair)

F

find_links() (in module src.linking) find_place_match() (in module src.aggregation)

finish_data() (in module main) full_firstname_match() (in module src.aggregation) fuse_hyphens() (in module src.preprocessing.preprocess)

G

get() (utility.evaluation_utils.Paths method) get_article_info() (in module src.postprocess) get_candidates() (in module src.linking) get_data_paths_iterative() (in module src.postprocess) get_field_value() (utility.settings.JsonConfigSettingsSource method) get_found_names() (in module src.postprocess) get_jsonl() (utility.evaluation_utils.Paths method) get_main_name() (in module utility.evaluation_utils)

get_pagenumbers() (in module utility.split_year) get_paramanera_token() (in module src.linking) get_person_context() (in module src.linking) get_person_context_reflevel() (in module src.linking) get_score() (utility.evaluation_utils.Scores method) get_structure_info() (in module src.postprocess) get_year_chunk_paths() (in module src.preprocessing.preprocess) GND_LIMIT (utility.settings.Settings attribute)

I

IN_WORD_SPLITTERS (src.preprocessing.preprocess.PreprocessConfig attribute) index_name_gnd (utility.settings.ElasticSettings attribute) index_name_wikidata (utility.settings.ElasticSettings attribute)

initialize_found_entry() (in module src.postprocess) initialize_found_place_entry() (in module src.postprocess) INKB_SCORE (utility.settings.Settings attribute)

J

JOB_ID (utility.settings.Settings attribute)

JsonConfigSettingsSource (class in utility.settings)

K

KONJ (src.preprocessing.preprocess.PreprocessConfig attribute)

L

label_entity() (in module utility.evaluation_utils) link_person() (in module src.linking)

LINKED_PERSONS_LIMIT (utility.settings.Settings attribute) load_abbrevs() (src.preprocessing.preprocess.PreprocessConfig method)

M

main module main() (in module main) (in module src.preprocessing.preprocess) (in module utility.compare) map_genitive_places() (in module src.aggregation) map_genitive_versions() (in module src.aggregation) merge_to_existing_aggregated_unit() (in module src.aggregation) MILVUS_HOST (utility.settings.Settings attribute) MILVUS_PORT (utility.settings.Settings attribute) model_config (utility.settings.ElasticSettings attribute) (utility.settings.Settings attribute) module main src src.aggregation src.evaluation src.linking src.postprocess src.preprocessing src.preprocessing.preprocess src.tag_flair utility utility.compare utility.evaluation_utils utility.linking_utils utility.settings utility.split_year utility.utils

O

offset_len_to_linking_input() (in module utility.utils) OIDC_TOKEN_URL (utility.settings.Settings attribute) only_abbrev_firstname_match() (in module src.aggregation)

only_firstname_match() (in module src.aggregation) only_lastname_match() (in module src.aggregation) others_match() (in module src.aggregation)

P

package_generator_output_paths() (in module src.tag_flair) parse_arguments() (in module utility.utils) password (utility.settings.ElasticSettings attribute) PATH_TO_ABBREVIATION_FILE (utility.settings.Settings attribute) PATH_TO_CA_CERT (utility.settings.Settings attribute) PATH_TO_GROUND_TRUTH (utility.settings.Settings attribute) PATH_TO_INPUT_FOLDERS (utility.settings.Settings attribute) PATH_TO_NER_MODEL_1 (utility.settings.Settings attribute) PATH_TO_NER_MODEL_2 (utility.settings.Settings attribute) PATH_TO_OUTFILE_FOLDER (utility.settings.Settings attribute) Paths (class in utility.evaluation_utils)

populate_year_dict() (in module src.postprocess) positive_int() (in module utility.utils) prep_name_for_elasticsearch_query() (in module utility.linking_utils) prep_person_entry() (in module src.linking) prep_person_out() (in module src.linking) prep_word() (in module src.linking) prep_year_data_for_tagging() (in module src.preprocessing.preprocess) prepare_field_value() (utility.settings.JsonConfigSettingsSource method) preprocess_file() (in module src.preprocessing.preprocess) PreprocessConfig (class in src.preprocessing.preprocess) process_page() (in module src.postprocess) PUNC (src.preprocessing.preprocess.PreprocessConfig attribute)

R

remove_obsolete_abbrevs() (in module src.linking)

S

save_data() (in module utility.utils) save_data_intermediate() (in module utility.utils) save_json() (utility.evaluation_utils.Paths method) Scores (class in utility.evaluation_utils) search_person_gnd() (in module utility.linking_utils) search_person_gnd_variantName() (in module utility.linking_utils) search_person_wikidata() (in module utility.linking_utils) SENTENCE_BATCH_SIZE (utility.settings.Settings attribute) SENTENCE_ENDING (src.preprocessing.preprocess.PreprocessConfig attribute) set_default() (in module utility.utils) Settings (class in utility.settings) settings_customise_sources() (utility.settings.Settings class method) setup_flair_tagger() (in module src.tag_flair) split_directory() (in module utility.split_year) split_sentences() (in module src.preprocessing.preprocess) src module

src.aggregation module src.evaluation module src.linking module src.postprocess module src.preprocessing module src.preprocessing.preprocess module src.tag_flair module start_preprocessing() (in module src.preprocessing.preprocess) str2bool() (in module utility.utils)

T

tag_year_data_and_save() (in module src.tag_flair) timed_execute_preprocessing() (in module src.preprocessing.preprocess)

tokenize() (in module src.preprocessing.preprocess) transkribus_xml_to_approx_word_coord() (in module utility.utils) txt_file_to_word_coord() (in module utility.utils)

U

update() (utility.evaluation_utils.Paths method) update_counter() (utility.evaluation_utils.Scores method) update_per_dict_score() (in module src.linking) USE_RICH_LOGGING (utility.settings.Settings attribute) username (utility.settings.ElasticSettings attribute) utility module utility.compare module

utility.evaluation_utils module utility.linking_utils module utility.settings module utility.split_year module utility.utils module

V

VD_API_TOKEN (utility.settings.Settings attribute) VD_CONTEXT_WINDOW_LEN (utility.settings.Settings attribute) VD_MAX_DIST (utility.settings.Settings attribute)

VD_MAX_RETRIES (utility.settings.Settings attribute) VD_QUERY_CHUNK_LEN (utility.settings.Settings attribute) VD_TIMEOUT (utility.settings.Settings attribute) VD_TIMEOUT_RETRY (utility.settings.Settings attribute)

W

WIKIDATA_LIMIT (utility.settings.Settings attribute)

write_sentences_to_outfile() (in module src.tag_flair)