|
|
# general
|
|
|
window.title=LIST 1.0
|
|
|
|
|
|
hyperlink.help=Help
|
|
|
button.language=SL
|
|
|
button.computeNgrams=Calculate
|
|
|
button.cancel=Cancel
|
|
|
|
|
|
# template
|
|
|
tab.corpusTab=Corpus
|
|
|
tab.filterTab=Filter
|
|
|
tab.characterLevelTabNew=Characters
|
|
|
tab.wordLevelTab=Word parts
|
|
|
tab.oneWordAnalysisTab=Words
|
|
|
tab.stringLevelTabNew2=Word sets
|
|
|
tab.aboutTab=About
|
|
|
|
|
|
# corpus tab
|
|
|
label.setCorpusLocation=Set corpus location
|
|
|
button.setCorpusLocation=Set location
|
|
|
label.readHeaderInfo=Read tax. from corpus files
|
|
|
checkBox.readHeaderInfo=
|
|
|
label.chooseResultsLocation=Choose result location
|
|
|
button.chooseResultsLocation=Set location
|
|
|
label.selectReader=Select reader
|
|
|
label.outputName=Output file name
|
|
|
label.punctuation=Decimal separator
|
|
|
|
|
|
label.corpusTab.chooseCorpusLocationH=Select the folder which contains the corpus. The folder should only contain one corpus and should not contain files that are not part of the corpus.
|
|
|
label.corpusTab.readHeaderInfoH=The program will read the taxonomy from corpus files. This might take a while.
|
|
|
label.corpusTab.chooseResultsLocationH=Choose result location
|
|
|
label.corpusTab.selectReaderH=Select reader
|
|
|
label.corpusTab.outputNameH=Output file name
|
|
|
label.corpusTab.punctuationH=Select the decimal separator used in export files.
|
|
|
|
|
|
# character analysis tab
|
|
|
label.stringLength=Number of characters
|
|
|
label.calculateFor=Calculate for
|
|
|
label.displayTaxonomy=Display taxonomies
|
|
|
label.dataLimit=Data limitations
|
|
|
label.msd=Morphosyntactic tag
|
|
|
label.taxonomy=Filter by taxonomy
|
|
|
label.minimalOccurrences=Min. nr. occurrences
|
|
|
label.minimalTaxonomy=Min. nr. tax. branches
|
|
|
label.minimalRelFre=Min. rel. frequency
|
|
|
label.taxonomySetOperation=Filter taxonomy by
|
|
|
label.solarFilters=Selected filters:
|
|
|
string.lemma=lemma
|
|
|
string.word=word
|
|
|
|
|
|
label.letter.stringLengthH=Enter the length of character strings.
|
|
|
label.letter.calculateForH=Character strings will be counted in the selected units.
|
|
|
label.letter.displayTaxonomyH=The output will also contain the distribution of character strings across the corpus taxonomy.
|
|
|
label.letter.msdH=Character strings will be counted only in words with the provided tag.
|
|
|
label.letter.taxonomyH=Character strings will be counted only in selected text types.
|
|
|
label.letter.minimalOccurrencesH=Character strings with fewer occurrences will not be included in the output.
|
|
|
label.letter.minimalTaxonomyH=Character strings that occur in fewer taxonomy branches will not be included in the output.
|
|
|
label.letter.taxonomySetOperationH=Extract information from texts that fit into at least one (union) or all (intersection) of the selected branches.
|
|
|
|
|
|
# word part tab
|
|
|
label.alsoVisualize=Also split by
|
|
|
label.lengthSearch=Search for word parts of a specified length
|
|
|
label.prefixLength=Length of initial part
|
|
|
label.suffixLength=Length of final part
|
|
|
label.listSearch=Search for word parts with a specified list
|
|
|
label.prefixList=List of initial parts
|
|
|
label.suffixList=List of final parts
|
|
|
|
|
|
label.wordPart.calculateForH=Word parts will be counted in the selected units.
|
|
|
label.wordPart.alsoVisualizeH=The output will also include the selected data.
|
|
|
label.wordPart.displayTaxonomyH=The output will also contain the distribution of word parts across the corpus taxonomy.
|
|
|
label.wordPart.prefixLengthH=Specify the length (in number of characters) of the initial word part.
|
|
|
label.wordPart.suffixLengthH=Specify the length (in number of characters) of the final word part.
|
|
|
label.wordPart.prefixListH=Separate the word parts with a semicolon (e.g. out; over)
|
|
|
label.wordPart.suffixListH=Separate the word parts with a semicolon (e.g. ation; ness).
|
|
|
label.wordPart.msdH=Word parts will only be counted in words with the specified tag.
|
|
|
label.wordPart.taxonomyH=Word parts will only be counted in the selected text types.
|
|
|
label.wordPart.minimalOccurrencesH=Units with the specified word part that occur fewer times will not be included in the output.
|
|
|
label.wordPart.minimalTaxonomyH=Units with the specified word part that are present in fewer taxonomy branches will not be included in the output.
|
|
|
label.wordPart.minimalRelFreH=Minimal relative frequency per million occurrences.
|
|
|
|
|
|
# word tab
|
|
|
label.writeMsdAtTheEnd=Split the morphosyntactic tag
|
|
|
|
|
|
label.word.calculateForH=Specify what the program should treat as the main unit for the output.
|
|
|
label.word.alsoVisualizeH=The output will also contain the selected data.
|
|
|
label.word.displayTaxonomyH=The output will also contain the distribution of units across the corpus taxonomy.
|
|
|
label.word.writeMsdAtTheEndH=The output will also include individual parts of morphosyntactic tags.
|
|
|
label.word.msdH=Only words with the specified tag will be counted.
|
|
|
label.word.taxonomyH=Only words in the selected text types will be counted.
|
|
|
label.word.minimalOccurrencesH=Words with fewer occurrences will not be included in the output.
|
|
|
label.word.minimalTaxonomyH=Words that occur in fewer taxonomy branches will not be included in the output.
|
|
|
|
|
|
# word sets tab
|
|
|
label.wordSet.calculateForH=Specify the units from which word sets will be extracted.
|
|
|
label.wordSet.alsoVisualizeH=The output will also include the selected data.
|
|
|
label.wordSet.displayTaxonomyH=The output will also contain the distribution of word sets across the corpus taxonomy.
|
|
|
label.wordSet.skipValueH=Enter the maximum number of words that can appear between two words in a word set.
|
|
|
label.wordSet.ngramValueH=The program will extract word sets with the specified number of tokens.
|
|
|
label.wordSet.notePunctuationsH=Word sets will include punctuation.
|
|
|
label.wordSet.collocabilityH=The program will also calculate collocability measures between words within the word set.
|
|
|
label.wordSet.msdH=The program will only count word sets with the specified tag.
|
|
|
label.wordSet.taxonomyH=Word sets will only be extracted from the selected taxonomy branches.
|
|
|
label.wordSet.minimalOccurrencesH=Word sets with fewer occurrences will not be included in the output.
|
|
|
label.wordSet.minimalTaxonomyH=Word sets that occur in fewer taxonomy branches will not be included in the output.
|
|
|
|
|
|
# punctuations
|
|
|
punctuation.COMMA=comma (,)
|
|
|
punctuation.POINT=point (.)
|
|
|
|
|
|
# calculate for
|
|
|
calculateFor.WORD=word
|
|
|
calculateFor.LOWERCASE_WORD=lowercase word
|
|
|
calculateFor.NORMALIZED_WORD=normalized word
|
|
|
calculateFor.LEMMA=lemma
|
|
|
calculateFor.MORPHOSYNTACTIC_SPECS=morphosyntactic tag
|
|
|
calculateFor.MORPHOSYNTACTIC_PROPERTY=morphosyntactic property
|
|
|
calculateFor.WORD_TYPE=word type
|
|
|
calculateFor.DIST_WORDS=word
|
|
|
calculateFor.DIST_LEMMAS=lemma
|
|
|
|
|
|
# n-grams
|
|
|
label.skipValue=Skip value
|
|
|
label.slowSpeedWarning=WARNING! USING THE ABOVE FILTER MAY DECREASE PROCESSING SPEED!
|
|
|
label.ngramValue=N-gram length
|
|
|
label.notePunctuations=Include punctuation
|
|
|
label.collocability=Collocability
|
|
|
|
|
|
# taxonomy set operations
|
|
|
taxonomySetOperation.UNION=union
|
|
|
taxonomySetOperation.INTERSECTION=intersection
|
|
|
|
|
|
# filtersSolar
|
|
|
filter.solarRegijaL=Region
|
|
|
filter.solarPredmetL=Subject
|
|
|
filter.solarRazredL=Class
|
|
|
filter.solarLetoL=Year
|
|
|
filter.solarSolaL=School
|
|
|
filter.solarVrstaBesedilaL=Text type
|
|
|
filter.solarRegija=region
|
|
|
filter.solarPredmet=subject
|
|
|
filter.solarRazred=class
|
|
|
filter.solarLeto=year
|
|
|
filter.solarSola=school
|
|
|
filter.solarVrstaBesedila=type
|
|
|
|
|
|
# messages
|
|
|
message.WARNING_CORPUS_NOT_FOUND=No suitable corpus files have been found in the selected directory.
|
|
|
message.WARNING_RESULTS_DIR_NOT_VALID=You do not have permission to access the selected directory.
|
|
|
message.WARNING_DIFFERING_NGRAM_LEVEL_AND_FILTER_TOKENS=The specified n-gram length and number of words do not match.
|
|
|
message.WARNING_DIFFERING_NGRAM_LEVEL_AND_FILTER_TOKENS_INFO=Choose another number or modify the filter.
|
|
|
message.WARNING_WORD_OR_LEMMA=Specify if you want to calculate statistics for words or lemmas.
|
|
|
message.WARNING_ONLY_NUMBERS_ALLOWED=Please enter a valid number.
|
|
|
message.WARNING_NUMBER_TOO_BIG=The entered number is larger than the number of taxonomy branches.
|
|
|
message.WARNING_MISMATCHED_NGRAM_AND_TOKENS_VALUES=The number for n-grams (%d) and number of tags included (%d) must match.
|
|
|
message.WARNING_MISSING_STRING_LENGTH=String length must be higher than 0. Length is set to default value (1).
|
|
|
message.WARNING_NO_TAXONOMY_FOUND=The program was unable to read the taxonomy from the corpus files. Please select another directory or a different corpus.
|
|
|
message.WARNING_NO_SOLAR_FILTERS_FOUND=The program was unable to read the filters from corpus files. Please select another location or a different corpus.
|
|
|
message.ERROR_WHILE_EXECUTING=An error occurred during program execution.
|
|
|
message.ERROR_WHILE_SAVING_RESULTS_TO_CSV=An error occurred while saving results.
|
|
|
message.ERROR_NOT_ENOUGH_MEMORY=Your memory is insufficient for analyzing such a large amount of data.
|
|
|
message.ERROR_NO_REGI_FILE_FOUND=Missing file \"%s\".
|
|
|
|
|
|
message.MISSING_NGRAM_LEVEL=N-gram level
|
|
|
message.MISSING_CALCULATE_FOR=Calculate for
|
|
|
message.MISSING_SKIP=""
|
|
|
message.MISSING_STRING_LENGTH=String length
|
|
|
message.MISMATCHED_STRING_LENGTH_AND_MSD_REGEX=String length and regex filter do not match.
|
|
|
|
|
|
message.NOTIFICATION_FOUND_X_FILES=Nr. of found files: %s
|
|
|
message.NOTIFICATION_CORPUS=Corpus: %s
|
|
|
message.NOTIFICATION_ANALYSIS_COMPLETED=Analysis complete. The results have been saved successfully.
|
|
|
message.NOTIFICATION_ANALYSIS_COMPLETED_NO_RESULTS=Analysis complete, but it was not possible to calculate statistics to match all the specified conditions.
|
|
|
message.RESULTS_PATH_SET_TO_DEFAULT=Save location is set to corpus location.
|
|
|
message.NOTIFICATION_ANALYSIS_CANCELED=The analysis was canceled.
|
|
|
|
|
|
message.ONGOING_NOTIFICATION_ANALYZING_FILE_X_OF_Y=Analyzing file %d of %d (%s) - Estimated time remaining %d s
|
|
|
message.CANCELING_NOTIFICATION=Canceled
|
|
|
|
|
|
message.LABEL_CORPUS_LOCATION_NOT_SET=Corpus location is not set.
|
|
|
message.LABEL_RESULTS_LOCATION_NOT_SET=Result location is not set.
|
|
|
message.LABEL_RESULTS_CORPUS_TYPE_NOT_SET=Corpus type is not set.
|
|
|
|
|
|
message.LABEL_SCANNING_CORPUS=Searching for and analyzing corpus files...
|
|
|
message.LABEL_SCANNING_SINGLE_FILE_CORPUS=Input analysis
|
|
|
message.COMPLETED=Completed
|
|
|
|
|
|
#message.TOOLTIP_chooseCorpusLocationB=Select folder which contains corpus. The folder should only contain one corpus and should not contain too many files that are not part of corpus.
|
|
|
#message.TOOLTIP_readHeaderInfoChB=If you select this option taxonomy will be read separately. This might take a while.
|
|
|
message.TOOLTIP_readNotePunctuationsChB=The punctuation in sentences is included in the analysis.
|
|
|
message.TOOLTIP_readDisplayTaxonomyChB=The output file will include the distribution across the taxonomy branches.
|
|
|
|
|
|
windowTitles.error=Error
|
|
|
windowTitles.warning=Warning
|
|
|
windowTitles.confirmation=Confirmation
|
|
|
|
|
|
# export header translations
|
|
|
exportHeader.corpus=Reader:
|
|
|
exportHeader.date=Date:
|
|
|
exportHeader.executionTime=Execution time:
|
|
|
exportHeader.analysis=Analysis:
|
|
|
exportHeader.analysis.letters=characters
|
|
|
exportHeader.analysis.wordParts=word parts
|
|
|
exportHeader.analysis.words=words
|
|
|
exportHeader.analysis.wordSets=word sets
|
|
|
exportHeader.numberLetters=Number of characters:
|
|
|
exportHeader.calculateFor=Calculate for:
|
|
|
exportHeader.alsoFilter=Also split by:
|
|
|
exportHeader.displayTaxonomies=Display taxonomy branches:
|
|
|
exportHeader.ngramLevel=N-gram level:
|
|
|
exportHeader.skipValue=Skip value:
|
|
|
exportHeader.notePunctuations=Include punctuation:
|
|
|
exportHeader.collocability=Collocability:
|
|
|
exportHeader.writeMSDAtTheEnd=Write tag at the end:
|
|
|
exportHeader.prefixLength=Initial part length:
|
|
|
exportHeader.suffixLength=Final part length:
|
|
|
exportHeader.prefixList=Initial part list:
|
|
|
exportHeader.suffixList=Final part list:
|
|
|
exportHeader.msd=Morphosyntactic tag:
|
|
|
exportHeader.taxonomy=Filter by taxonomy:
|
|
|
exportHeader.minOccurrences=Min. nr. occurrences:
|
|
|
exportHeader.minTaxonomies=Min. nr. taxonomy branches:
|
|
|
exportHeader.minRelFre=Min. rel. frequency nr.:
|
|
|
exportHeader.additionalFilters=Additional filters:
|
|
|
exportHeader.yes=yes
|
|
|
exportHeader.no=no
|
|
|
exportHeader.taxonomySetOperation=Filter taxonomy by:
|
|
|
|
|
|
# export table header translations
|
|
|
exportTable.skippedWords=Skipped words
|
|
|
exportTable.lettersSmall=Characters (lower case)
|
|
|
exportTable.wordsSmall=Lemma (lower case)
|
|
|
exportTable.wordBeginning=Initial part of the word
|
|
|
exportTable.wordEnding=Final part of the word
|
|
|
exportTable.wordRest=The rest of the word
|
|
|
exportTable.totalRelativeFrequency=Total relative frequency (over one million occurrences)
|
|
|
exportTable.absoluteFrequency=Absolute frequency
|
|
|
exportTable.percentage=Share
|
|
|
exportTable.relativeFrequency=Relative frequency
|
|
|
exportTable.msd=msd
|
|
|
# parts
|
|
|
exportTable.part.word=words:
|
|
|
exportTable.part.lowercaseWord=lowercase words:
|
|
|
exportTable.part.normalizedWord=normalized words:
|
|
|
exportTable.part.lemma=lemmas:
|
|
|
exportTable.part.msd=msd:
|
|
|
exportTable.part.msdProperty=msd property:
|
|
|
exportTable.part.wordType=word type:
|
|
|
|
|
|
exportTable.part.letterSet=character set
|
|
|
exportTable.part.word2=word
|
|
|
exportTable.part.lowercaseWord2=lowercase word
|
|
|
exportTable.part.normalizedWord2=normalized word
|
|
|
exportTable.part.lemma2=lemma
|
|
|
exportTable.part.msd2=msd
|
|
|
exportTable.part.msdProperty2=msd property
|
|
|
exportTable.part.wordType2=word type
|
|
|
|
|
|
exportTable.part.letterSet2=Share of total sum of all letter sets
|
|
|
exportTable.part.letterSet3=Letter set
|
|
|
exportTable.part.word3=Word
|
|
|
exportTable.part.lowercaseWord3=Lowercase word
|
|
|
exportTable.part.normalizedWord3=Normalized word
|
|
|
exportTable.part.lemma3=Lemma
|
|
|
exportTable.part.msd3=Msd
|
|
|
exportTable.part.msdProperty3=Msd property
|
|
|
exportTable.part.wordType3=Word type
|
|
|
|
|
|
exportTable.part.set=set
|
|
|
exportTable.part.share=Absolute share of
|
|
|
exportTable.part.absoluteFrequency=Absolute frequency of
|
|
|
exportTable.part.totalFound=Total sum of all
|
|
|
exportTable.part.totalFoundLetters=Total sum of all found letters of
|
|
|
exportTable.part.totalSumString=Total sum of
|
|
|
exportTable.part.totalSumLetters=Total sum of all letters of
|
|
|
|
|
|
# generated files names
|
|
|
exportFileName.letters=letters
|
|
|
exportFileName.wordParts=word-parts
|
|
|
exportFileName.words=words
|
|
|
exportFileName.wordSets=word-sets
|
|
|
exportFileName.gram=-gram
|
|
|
exportFileName.skip=-skip
|
|
|
|
|
|
about.header=LIST – Corpus Extraction Tool\nVersion: 1.0 (Last update: 21 March 2019)\nAuthors: Luka Krsnik, Špela Arhar Holdt, Jaka Čibej, Kaja Dobrovoljc, Aleksander\n Ključevšek, Simon Krek, Marko Robnik Šikonja
|
|
|
about.description=The LIST corpus extraction tool is a program for extracting lists from text corpora on the\n levels of characters, word parts, words, and word sets. The program was developed within\n the New Grammar of Modern Standard Slovene: Resource and Methods project (J6-8256),\n which was financially supported by the Slovenian Research Agency between 2017 and 2020.\n The authors acknowledge the financial support from the Slovenian Research Agency\n (research core funding No. P6-0411 Language Resources and Technologies for Slovene).\n
|
|
|
about.signature=Publisher: Centre for Language Resources and Technologies, University of Ljubljana,\nJožef Stefan Institute,\nFaculty of Computer and Information Science, University of Ljubljana
|
|
|
about.footer=Maintenance: Centre for Language Resources and Technologies, University of Ljubljana\nThe program is available under the GNU General Public Licence (version 3) at\n CLARIN.si and GitHub.
|
|
|
about.links=Links:
|
|
|
#about.text=LIST – Corpus Extraction Tool\nVersion: 1.0 (Last update: 21 March 2019)\nAuthors: Luka Krsnik, Špela Arhar Holdt, Jaka Čibej, Kaja Dobrovoljc, Aleksander\n Ključevšek, Simon Krek, Marko Robnik Šikonja\n\nThe LIST corpus extraction tool is a program for extracting lists from text corpora on the\n levels of characters, word parts, words, and word sets. The program was developed within\n the New Grammar of Modern Standard Slovene: Resource and Methods project (J6-8256),\n which was financially supported by the Slovenian Research Agency between 2017 and 2020.\n\n\nPublisher: Centre for Language Resources and Technologies, University of Ljubljana,\nJožef Stefan Institute,\nFaculty of Computer and Information Science, University of Ljubljana\n\nMaintenance: Centre for Language Resources and Technologies, University of Ljubljana\nThe program is available under the GNU General Public Licence (version 3) at
|
