lemmar: Dictionary Based Lemmatization

#' Asturian Lemma Dictionary
#'
#' A dataset containing Asturian tokens and corresponding lemmas. This data set
#' comes from \url{http://www.lexiconista.com}, and is made freely available
#' under the ODbL 1.0 license (\url{https://opendatacommons.org/licenses/odbl/summary}).
#' Note that tokes with more than one lemma were dropped from the data set.
#'
#' @details
#' \itemize{
#'   \item token. An inflected token with affixes
#'   \item lemma. A base form
#' }
#'
#' @docType data
#' @keywords datasets
#' @name hash_lemma_ast
#' @usage data(hash_lemma_ast)
#' @format A data frame with 104375 rows and 2 variables
#' @references \url{http://www.lexiconista.com}
NULL


#' Bulgarian Lemma Dictionary
#'
#' A dataset containing Bulgarian tokens and corresponding lemmas. This data set
#' comes from \url{http://www.lexiconista.com}, and is made freely available
#' under the ODbL 1.0 license (\url{https://opendatacommons.org/licenses/odbl/summary}).
#' Note that tokes with more than one lemma were dropped from the data set.
#'
#' @details
#' \itemize{
#'   \item token. An inflected token with affixes
#'   \item lemma. A base form
#' }
#'
#' @docType data
#' @keywords datasets
#' @name hash_lemma_bg
#' @usage data(hash_lemma_bg)
#' @format A data frame with 26254 rows and 2 variables
#' @references \url{http://www.lexiconista.com}
NULL


#' Catalan Lemma Dictionary
#'
#' A dataset containing Catalan tokens and corresponding lemmas. This data set
#' comes from \url{http://www.lexiconista.com}, and is made freely available
#' under the ODbL 1.0 license (\url{https://opendatacommons.org/licenses/odbl/summary}).
#' Note that tokes with more than one lemma were dropped from the data set.
#'
#' @details
#' \itemize{
#'   \item token. An inflected token with affixes
#'   \item lemma. A base form
#' }
#'
#' @docType data
#' @keywords datasets
#' @name hash_lemma_ca
#' @usage data(hash_lemma_ca)
#' @format A data frame with 576560 rows and 2 variables
#' @references \url{http://www.lexiconista.com}
NULL


#' Czech Lemma Dictionary
#'
#' A dataset containing Czech tokens and corresponding lemmas. This data set
#' comes from \url{http://www.lexiconista.com}, and is made freely available
#' under the ODbL 1.0 license (\url{https://opendatacommons.org/licenses/odbl/summary}).
#' Note that tokes with more than one lemma were dropped from the data set.
#'
#' @details
#' \itemize{
#'   \item token. An inflected token with affixes
#'   \item lemma. A base form
#' }
#'
#' @docType data
#' @keywords datasets
#' @name hash_lemma_cs
#' @usage data(hash_lemma_cs)
#' @format A data frame with 33729 rows and 2 variables
#' @references \url{http://www.lexiconista.com}
NULL


#' English Lemma Dictionary
#'
#' A dataset containing English tokens and corresponding lemmas. This data set
#' comes from \url{http://www.lexiconista.com}, and is made freely available
#' under the ODbL 1.0 license (\url{https://opendatacommons.org/licenses/odbl/summary}).
#' Note that tokes with more than one lemma were dropped from the data set.
#'
#' @details
#' \itemize{
#'   \item token. An inflected token with affixes
#'   \item lemma. A base form
#' }
#'
#' @docType data
#' @keywords datasets
#' @name hash_lemma_en
#' @usage data(hash_lemma_en)
#' @format A data frame with 41410 rows and 2 variables
#' @references \url{http://www.lexiconista.com}
NULL


#' Estonian Lemma Dictionary
#'
#' A dataset containing Estonian tokens and corresponding lemmas. This data set
#' comes from \url{http://www.lexiconista.com}, and is made freely available
#' under the ODbL 1.0 license (\url{https://opendatacommons.org/licenses/odbl/summary}).
#' Note that tokes with more than one lemma were dropped from the data set.
#'
#' @details
#' \itemize{
#'   \item token. An inflected token with affixes
#'   \item lemma. A base form
#' }
#'
#' @docType data
#' @keywords datasets
#' @name hash_lemma_et
#' @usage data(hash_lemma_et)
#' @format A data frame with 66351 rows and 2 variables
#' @references \url{http://www.lexiconista.com}
NULL


#' French Lemma Dictionary
#'
#' A dataset containing French tokens and corresponding lemmas. This data set
#' comes from \url{http://www.lexiconista.com}, and is made freely available
#' under the ODbL 1.0 license (\url{https://opendatacommons.org/licenses/odbl/summary}).
#' Note that tokes with more than one lemma were dropped from the data set.
#'
#' @details
#' \itemize{
#'   \item token. An inflected token with affixes
#'   \item lemma. A base form
#' }
#'
#' @docType data
#' @keywords datasets
#' @name hash_lemma_fr
#' @usage data(hash_lemma_fr)
#' @format A data frame with 210381 rows and 2 variables
#' @references \url{http://www.lexiconista.com}
NULL


#' Galician Lemma Dictionary
#'
#' A dataset containing Galician tokens and corresponding lemmas. This data set
#' comes from \url{http://www.lexiconista.com}, and is made freely available
#' under the ODbL 1.0 license (\url{https://opendatacommons.org/licenses/odbl/summary}).
#' Note that tokes with more than one lemma were dropped from the data set.
#'
#' @details
#' \itemize{
#'   \item token. An inflected token with affixes
#'   \item lemma. A base form
#' }
#'
#' @docType data
#' @keywords datasets
#' @name hash_lemma_gl
#' @usage data(hash_lemma_gl)
#' @format A data frame with 380847 rows and 2 variables
#' @references \url{http://www.lexiconista.com}
NULL


#' German Lemma Dictionary
#'
#' A dataset containing German tokens and corresponding lemmas. This data set
#' comes from \url{http://www.lexiconista.com}, and is made freely available
#' under the ODbL 1.0 license (\url{https://opendatacommons.org/licenses/odbl/summary}).
#' Note that tokes with more than one lemma were dropped from the data set.
#'
#' @details
#' \itemize{
#'   \item token. An inflected token with affixes
#'   \item lemma. A base form
#' }
#'
#' @docType data
#' @keywords datasets
#' @name hash_lemma_de
#' @usage data(hash_lemma_de)
#' @format A data frame with 351479 rows and 2 variables
#' @references \url{http://www.lexiconista.com}
NULL


#' Hungarian Lemma Dictionary
#'
#' A dataset containing Hungarian tokens and corresponding lemmas. This data set
#' comes from \url{http://www.lexiconista.com}, and is made freely available
#' under the ODbL 1.0 license (\url{https://opendatacommons.org/licenses/odbl/summary}).
#' Note that tokes with more than one lemma were dropped from the data set.
#'
#' @details
#' \itemize{
#'   \item token. An inflected token with affixes
#'   \item lemma. A base form
#' }
#'
#' @docType data
#' @keywords datasets
#' @name hash_lemma_hu
#' @usage data(hash_lemma_hu)
#' @format A data frame with 35723 rows and 2 variables
#' @references \url{http://www.lexiconista.com}
NULL


#' Irish Lemma Dictionary
#'
#' A dataset containing Irish tokens and corresponding lemmas. This data set
#' comes from \url{http://www.lexiconista.com}, and is made freely available
#' under the ODbL 1.0 license (\url{https://opendatacommons.org/licenses/odbl/summary}).
#' Note that tokes with more than one lemma were dropped from the data set.
#'
#' @details
#' \itemize{
#'   \item token. An inflected token with affixes
#'   \item lemma. A base form
#' }
#'
#' @docType data
#' @keywords datasets
#' @name hash_lemma_ga
#' @usage data(hash_lemma_ga)
#' @format A data frame with 353339 rows and 2 variables
#' @references \url{http://www.lexiconista.com}
NULL


#' Manx Gaelic Lemma Dictionary
#'
#' A dataset containing Manx Gaelic tokens and corresponding lemmas. This data set
#' comes from \url{http://www.lexiconista.com}, and is made freely available
#' under the ODbL 1.0 license (\url{https://opendatacommons.org/licenses/odbl/summary}).
#' Note that tokes with more than one lemma were dropped from the data set.
#'
#' @details
#' \itemize{
#'   \item token. An inflected token with affixes
#'   \item lemma. A base form
#' }
#'
#' @docType data
#' @keywords datasets
#' @name hash_lemma_gv
#' @usage data(hash_lemma_gv)
#' @format A data frame with 60494 rows and 2 variables
#' @references \url{http://www.lexiconista.com}
NULL


#' Italian Lemma Dictionary
#'
#' A dataset containing Italian tokens and corresponding lemmas. This data set
#' comes from \url{http://www.lexiconista.com}, and is made freely available
#' under the ODbL 1.0 license (\url{https://opendatacommons.org/licenses/odbl/summary}).
#' Note that tokes with more than one lemma were dropped from the data set.
#'
#' @details
#' \itemize{
#'   \item token. An inflected token with affixes
#'   \item lemma. A base form
#' }
#'
#' @docType data
#' @keywords datasets
#' @name hash_lemma_it
#' @usage data(hash_lemma_it)
#' @format A data frame with 326728 rows and 2 variables
#' @references \url{http://www.lexiconista.com}
NULL


#' Persian/Farsi Lemma Dictionary
#'
#' A dataset containing Persian/Farsi tokens and corresponding lemmas. This data set
#' comes from \url{http://www.lexiconista.com}, and is made freely available
#' under the ODbL 1.0 license (\url{https://opendatacommons.org/licenses/odbl/summary}).
#' Note that tokes with more than one lemma were dropped from the data set.
#'
#' @details
#' \itemize{
#'   \item token. An inflected token with affixes
#'   \item lemma. A base form
#' }
#'
#' @docType data
#' @keywords datasets
#' @name hash_lemma_fa
#' @usage data(hash_lemma_fa)
#' @format A data frame with 6177 rows and 2 variables
#' @references \url{http://www.lexiconista.com}
NULL


#' Polish Lemma Dictionary
#'
#' A dataset containing Polish tokens and corresponding lemmas. This data set
#' comes from \url{http://www.lexiconista.com}, and is made freely available
#' under the ODbL 1.0 license (\url{https://opendatacommons.org/licenses/odbl/summary}).
#' Note that tokes with more than one lemma were dropped from the data set.
#'
#' @details
#' \itemize{
#'   \item token. An inflected token with affixes
#'   \item lemma. A base form
#' }
#'
#' @docType data
#' @keywords datasets
#' @name hash_lemma_pl
#' @usage data(hash_lemma_pl)
#' @format A data frame with 3188220 rows and 2 variables
#' @references \url{http://www.lexiconista.com}
NULL


#' Portuguese Lemma Dictionary
#'
#' A dataset containing Portuguese tokens and corresponding lemmas. This data set
#' comes from \url{http://www.lexiconista.com}, and is made freely available
#' under the ODbL 1.0 license (\url{https://opendatacommons.org/licenses/odbl/summary}).
#' Note that tokes with more than one lemma were dropped from the data set.
#'
#' @details
#' \itemize{
#'   \item token. An inflected token with affixes
#'   \item lemma. A base form
#' }
#'
#' @docType data
#' @keywords datasets
#' @name hash_lemma_pt
#' @usage data(hash_lemma_pt)
#' @format A data frame with 799991 rows and 2 variables
#' @references \url{http://www.lexiconista.com}
NULL


#' Romanian Lemma Dictionary
#'
#' A dataset containing Romanian tokens and corresponding lemmas. This data set
#' comes from \url{http://www.lexiconista.com}, and is made freely available
#' under the ODbL 1.0 license (\url{https://opendatacommons.org/licenses/odbl/summary}).
#' Note that tokes with more than one lemma were dropped from the data set.
#'
#' @details
#' \itemize{
#'   \item token. An inflected token with affixes
#'   \item lemma. A base form
#' }
#'
#' @docType data
#' @keywords datasets
#' @name hash_lemma_ro
#' @usage data(hash_lemma_ro)
#' @format A data frame with 296754 rows and 2 variables
#' @references \url{http://www.lexiconista.com}
NULL


#' Scottish Gaelic Lemma Dictionary
#'
#' A dataset containing Scottish Gaelic tokens and corresponding lemmas. This data set
#' comes from \url{http://www.lexiconista.com}, and is made freely available
#' under the ODbL 1.0 license (\url{https://opendatacommons.org/licenses/odbl/summary}).
#' Note that tokes with more than one lemma were dropped from the data set.
#'
#' @details
#' \itemize{
#'   \item token. An inflected token with affixes
#'   \item lemma. A base form
#' }
#'
#' @docType data
#' @keywords datasets
#' @name hash_lemma_gd
#' @usage data(hash_lemma_gd)
#' @format A data frame with 46627 rows and 2 variables
#' @references \url{http://www.lexiconista.com}
NULL


#' Slovak Lemma Dictionary
#'
#' A dataset containing Slovak tokens and corresponding lemmas. This data set
#' comes from \url{http://www.lexiconista.com}, and is made freely available
#' under the ODbL 1.0 license (\url{https://opendatacommons.org/licenses/odbl/summary}).
#' Note that tokes with more than one lemma were dropped from the data set.
#'
#' @details
#' \itemize{
#'   \item token. An inflected token with affixes
#'   \item lemma. A base form
#' }
#'
#' @docType data
#' @keywords datasets
#' @name hash_lemma_sk
#' @usage data(hash_lemma_sk)
#' @format A data frame with 836909 rows and 2 variables
#' @references \url{http://www.lexiconista.com}
NULL


#' Slovene Lemma Dictionary
#'
#' A dataset containing Slovene tokens and corresponding lemmas. This data set
#' comes from \url{http://www.lexiconista.com}, and is made freely available
#' under the ODbL 1.0 license (\url{https://opendatacommons.org/licenses/odbl/summary}).
#' Note that tokes with more than one lemma were dropped from the data set.
#'
#' @details
#' \itemize{
#'   \item token. An inflected token with affixes
#'   \item lemma. A base form
#' }
#'
#' @docType data
#' @keywords datasets
#' @name hash_lemma_sl
#' @usage data(hash_lemma_sl)
#' @format A data frame with 95895 rows and 2 variables
#' @references \url{http://www.lexiconista.com}
NULL


#' Spanish Lemma Dictionary
#'
#' A dataset containing Spanish tokens and corresponding lemmas. This data set
#' comes from \url{http://www.lexiconista.com}, and is made freely available
#' under the ODbL 1.0 license (\url{https://opendatacommons.org/licenses/odbl/summary}).
#' Note that tokes with more than one lemma were dropped from the data set.
#'
#' @details
#' \itemize{
#'   \item token. An inflected token with affixes
#'   \item lemma. A base form
#' }
#'
#' @docType data
#' @keywords datasets
#' @name hash_lemma_es
#' @usage data(hash_lemma_es)
#' @format A data frame with 485670 rows and 2 variables
#' @references \url{http://www.lexiconista.com}
NULL


#' Swedish Lemma Dictionary
#'
#' A dataset containing Swedish tokens and corresponding lemmas. This data set
#' comes from \url{http://www.lexiconista.com}, and is made freely available
#' under the ODbL 1.0 license (\url{https://opendatacommons.org/licenses/odbl/summary}).
#' Note that tokes with more than one lemma were dropped from the data set.
#'
#' @details
#' \itemize{
#'   \item token. An inflected token with affixes
#'   \item lemma. A base form
#' }
#'
#' @docType data
#' @keywords datasets
#' @name hash_lemma_sv
#' @usage data(hash_lemma_sv)
#' @format A data frame with 645842 rows and 2 variables
#' @references \url{http://www.lexiconista.com}
NULL


#' Ukrainian Lemma Dictionary
#'
#' A dataset containing Ukrainian tokens and corresponding lemmas. This data set
#' comes from \url{http://www.lexiconista.com}, and is made freely available
#' under the ODbL 1.0 license (\url{https://opendatacommons.org/licenses/odbl/summary}).
#' Note that tokes with more than one lemma were dropped from the data set.
#'
#' @details
#' \itemize{
#'   \item token. An inflected token with affixes
#'   \item lemma. A base form
#' }
#'
#' @docType data
#' @keywords datasets
#' @name hash_lemma_uk
#' @usage data(hash_lemma_uk)
#' @format A data frame with 187870 rows and 2 variables
#' @references \url{http://www.lexiconista.com}
NULL


#' Welsh Lemma Dictionary
#'
#' A dataset containing Welsh tokens and corresponding lemmas. This data set
#' comes from \url{http://www.lexiconista.com}, and is made freely available
#' under the ODbL 1.0 license (\url{https://opendatacommons.org/licenses/odbl/summary}).
#' Note that tokes with more than one lemma were dropped from the data set.
#'
#' @details
#' \itemize{
#'   \item token. An inflected token with affixes
#'   \item lemma. A base form
#' }
#'
#' @docType data
#' @keywords datasets
#' @name hash_lemma_cy
#' @usage data(hash_lemma_cy)
#' @format A data frame with 347333 rows and 2 variables
#' @references \url{http://www.lexiconista.com}
NULL