@inproceedings{bc16870b52e74e12a893c0ef56723677,
title = "A French Corpus of Qu{\'e}bec{\textquoteright}s Parliamentary Debates",
abstract = "Parliamentary debates offer a window on political stances as well as a repository of linguistic and semantic knowledge. They provide insights and reasons for laws and regulations that impact electors in their everyday life. One such resource is the transcribed debates available online from the Assembl{\'e}e Nationale du Qu{\'e}bec (ANQ). This paper describes the effort to convert the online ANQ debates from various HTML formats into a standardized ParlaMint TEI annotated corpus and to enrich it with annotations extracted from related unstructured members and political parties list. The resulting resource includes 88 years of debates over a span of 114 years with more than 33.3 billion words. The addition of linguistic annotations is detailed as well as a quantitative analysis of part-of-speech tags and distribution of utterances across the corpus.",
keywords = "French, ParlaMint, Provincial Parliament, Qu{\'e}bec",
author = "M{\'e}nard, \{Pierre Andr{\'e}\} and Desislava Aleksandrova",
note = "Publisher Copyright: {\textcopyright} European Language Resources Association (ELRA).; 2022 Workshop on Creating, Enriching and Using Parliamentary Corpora, ParlaCLARIN III 2022 ; Conference date: 20-06-2022 Through 25-06-2022",
year = "2022",
language = "English",
series = "ParlaCLARIN III 2022 - Workshop on Creating, Enriching and Using Parliamentary Corpora, Proceedings - as part of the 13th Edition of the Language Resources and Evaluation Conference, LREC 2022",
publisher = "European Language Resources Association (ELRA)",
pages = "25--32",
editor = "Darja Fiser and Maria Eskevich and Jakob Lenardic and \{de Jong\}, Franciska",
booktitle = "ParlaCLARIN III 2022 - Workshop on Creating, Enriching and Using Parliamentary Corpora, Proceedings - as part of the 13th Edition of the Language Resources and Evaluation Conference, LREC 2022",
}