|
||||||||||
| PREV NEXT | FRAMES NO FRAMES | |||||||||
| gov.llnl.* |
|---|
| gov.llnl.ontology.mapreduce.ingest.IngestCorpusMR | ||
|---|---|---|
public static final String |
DEFAULT_SPLITTER |
"gov.llnl.ontology.text.sentsplit.OpenNlpMESentenceSplitter" |
public static final String |
DEFAULT_TAGGER |
"gov.llnl.ontology.text.tag.OpenNlpMEPOSTagger" |
public static final String |
DEFAULT_TOKENIZER |
"gov.llnl.ontology.text.tokenize.OpenNlpMETokenizer" |
| gov.llnl.ontology.mapreduce.ingest.OneLinePerDocExtractorMR | ||
|---|---|---|
public static final String |
ABOUT |
"Extracts the raw tokenized text from a corpus and stores it to hdfs" |
public static final String |
MR_NAME |
"OneLinePerDocExtractorMR" |
public static final String |
USE_HEADER |
"gov.llnl.ontology.mapreduce.ingest.OneLinePerDocExtractorMR.header" |
| gov.llnl.ontology.mapreduce.ingest.ParsedDocExtractorMR | ||
|---|---|---|
public static final String |
ABOUT |
"Extracts the dependency parsed data for a corpus and stores it to hdfs." |
| gov.llnl.ontology.mapreduce.stats.DependencyOccurrenceCountMR | ||
|---|---|---|
public static final String |
ABOUT |
"Computes the co-occurrence frequencies between words that are connected by dependency paths. Dependency paths will be valided by a DependencyPathAcceptor and must be shorter than a finite path length. The final word in each dependency path will be the co-occurring word with the root of the path, and the final dependency connecting them may also be included in the word form. If no corpus is specified, then all corpora will be used to compute the frequencies. The co-occurrence counts will be stored in reduce parts on hdfs under the specified <outdir>." |
public static final String |
CONF_PREFIX |
"gov.llnl.ontology.mapreduce.stats.DependencyOccurrenceCountMR" |
public static final String |
DEFAULT_ACCEPTOR |
"edu.ucla.sspace.dependency.UniversalAcceptor" |
public static final String |
PATH_ACCEPTOR |
"gov.llnl.ontology.mapreduce.stats.DependencyOccurrenceCountMR.pathAcceptor" |
public static final String |
PATH_LENGTH |
"gov.llnl.ontology.mapreduce.stats.DependencyOccurrenceCountMR.pathLength" |
public static final String |
USE_RELATION |
"gov.llnl.ontology.mapreduce.stats.DependencyOccurrenceCountMR.useRelation" |
| gov.llnl.ontology.mapreduce.stats.POSCountMR | ||
|---|---|---|
public static final String |
ABOUT |
"Computes pos counts from a particular corpus. If no corpus is specified, then all corpora will be used to compute the frequencies. The co-occurrence counts will be stored in reduce parts on hdfs under the specified <outdir>." |
| gov.llnl.ontology.mapreduce.stats.SemEvalPrinter | ||
|---|---|---|
public static final String |
ABOUT |
"Extracts the dependency parsed data for SemEval corpora and stores it to hdfs." |
| gov.llnl.ontology.mapreduce.stats.TagDocumentMR | ||
|---|---|---|
public static final String |
ABOUT |
"Computes co-occurrence links between tags in a particular corpus. If no corpus is specified, then all corpora will be used to compute the frequencies. The co-occurrence counts will be stored in reduce parts on hdfs under the specified <outdir>." |
| gov.llnl.ontology.mapreduce.stats.TagNetworkMR | ||
|---|---|---|
public static final String |
ABOUT |
"Computes co-occurrence links between tags in a particular corpus. If no corpus is specified, then all corpora will be used to compute the frequencies. The co-occurrence counts will be stored in reduce parts on hdfs under the specified <outdir>." |
| gov.llnl.ontology.mapreduce.stats.TagOccurrenceMR | ||
|---|---|---|
public static final String |
ABOUT |
"Computes co-occurrence links between tags in a particular corpus. If no corpus is specified, then all corpora will be used to compute the frequencies. The co-occurrence counts will be stored in reduce parts on hdfs under the specified <outdir>." |
| gov.llnl.ontology.mapreduce.stats.TagWordStatsMR | ||
|---|---|---|
public static final String |
ABOUT |
"Computes the co-occurrence frequency between document tags and words in the documents for a particular corpus. If no corpus is specified, all documents will be used. The co-occurrence counts will be stored in reduce parts on hdfs under the specified <outdir" |
| gov.llnl.ontology.mapreduce.stats.TermDocOccurrenceCountMR | ||
|---|---|---|
public static final String |
ABOUT |
"Computes a bag of words co-occurrence count between all words in a document. Each document co-occurrence will only be counted once for each term pair from a particular corpus in a CorpusTable. The resulting counts will be stored on HDFS." |
| gov.llnl.ontology.mapreduce.stats.TermDocumentCountMR | ||
|---|---|---|
public static final String |
ABOUT |
"Computes the term document matrix for a particular corpus and stores the frequencies to HDFS. Terms will be emitted as they are and documents will be tagged using their key as stored in the CorpusTable specified." |
| gov.llnl.ontology.mapreduce.stats.TokenCountMR | ||
|---|---|---|
public static final String |
ABOUT |
"Computes token counts from a particular corpus. If no corpus is specified, then all corpora will be used to compute the frequencies. The co-occurrence counts will be stored in reduce parts on hdfs under the specified <outdir>." |
| gov.llnl.ontology.mapreduce.stats.WordnetShortestPathMR | ||
|---|---|---|
public static final String |
CONF_BASE |
"gov.llnl.ontology.mapreduce.stats.WordnetShortestPathMR" |
public static final String |
TEMP_TERM_PAIR_PATH |
"wordnet-pair-file" |
public static final String |
WORDNET |
"gov.llnl.ontology.mapreduce.stats.WordnetShortestPathMR.wordnet" |
| gov.llnl.ontology.mapreduce.stats.WordOccurrenceCountMR | ||
|---|---|---|
public static final String |
ABOUT |
"Computes word co-occurrence frequencies from a particular corpus. If no corpus is specified, then all corpora will be used to compute the frequencies. The co-occurrence counts will be stored in reduce parts on hdfs under the specified <outdir>." |
public static final String |
CONF_PREFIX |
"gov.llnl.ontology.mapreduce.stats.WordOccurrenceCountMR" |
public static final String |
MR_NAME |
"WordOccurrenceCountMR" |
public static final String |
USE_ORDER |
"gov.llnl.ontology.mapreduce.stats.WordOccurrenceCountMR.useOrder" |
public static final String |
USE_POS |
"gov.llnl.ontology.mapreduce.stats.WordOccurrenceCountMR.usePos" |
public static final String |
WINDOW_SIZE |
"gov.llnl.ontology.mapreduce.stats.WordOccurrenceCountMR.windowSize" |
| gov.llnl.ontology.mapreduce.stats.WordsiMR | ||
|---|---|---|
public static final String |
ABOUT |
"Computes context vectors for a wordsi model using a particular DependencyContextGenerator. The computed context vectors will be in a pure text format with the context id as the first token and then a list of feature,count pairs. The full form of each feature will be written, rather than an index matched to each feature since mappers are unable to coordinate feature index mappings." |
public static final String |
CONF_PREFIX |
"gov.llnl.ontology.mapreduce.stats.WordsiMR" |
public static final String |
DEFAULT_ACCEPTOR |
"edu.ucla.sspace.dependency.UniversalPathAcceptor" |
public static final String |
DEFAULT_WEIGHT |
"edu.ucla.sspace.dependency.FlatPathWeight" |
public static final String |
DEPENDENCY_BASIS |
"gov.llnl.ontology.mapreduce.stats.WordsiMR.dependencyBasis" |
public static final String |
PATH_ACCEPTOR |
"gov.llnl.ontology.mapreduce.stats.WordsiMR.pathAcceptor" |
public static final String |
PATH_LENGTH |
"gov.llnl.ontology.mapreduce.stats.WordsiMR.pathLength" |
public static final String |
PATH_WEIGHT |
"gov.llnl.ontology.mapreduce.stats.WordsiMR.pathWeight" |
public static final String |
USE_ORDERING |
"gov.llnl.ontology.mapreduce.stats.WordsiMR.useOrdering" |
public static final String |
USE_POS |
"gov.llnl.ontology.mapreduce.stats.WordsiMR.usePos" |
| gov.llnl.ontology.mapreduce.table.TrinidadTable | ||
|---|---|---|
public static final String |
ALL_CORPORA |
"" |
public static final String |
ANNOTATION_CF |
"annotations" |
public static final String |
ANNOTATION_SENTENCE |
"sentence" |
public static final String |
ANNOTATION_TOKEN |
"token" |
public static final String |
CATEGORY_COLUMN |
"categories" |
public static final String |
DOC_ID |
"id" |
public static final String |
DOC_KEY |
"key" |
public static final String |
LABEL_CF |
"wordListLabels" |
public static final String |
META_CF |
"meta" |
public static final String |
SENSE_SENTENCE_PREFIX |
"wss" |
public static final String |
SENSE_TOKEN_PREFIX |
"wst" |
public static final String |
SOURCE_CF |
"src" |
public static final String |
SOURCE_ID |
"id" |
public static final String |
SOURCE_IDCOL |
"src:id" |
public static final String |
SOURCE_NAME |
"name" |
public static final String |
SOURCE_NAMECOL |
"src:name" |
public static final String |
TABLE_NAME |
"trinidad_table" |
public static final String |
TEXT_CF |
"text" |
public static final String |
TEXT_ORIGINAL |
"orig" |
public static final String |
TEXT_ORIGINAL_COL |
"text:orig" |
public static final String |
TEXT_RAW |
"raw" |
public static final String |
TEXT_RAW_COL |
"text:raw" |
public static final String |
TEXT_TITLE |
"title" |
public static final String |
TEXT_TITLE_COL |
"text:title" |
public static final String |
TEXT_TYPE |
"text" |
public static final String |
TEXT_TYPE_COL |
"text:text" |
public static final String |
XML_MIME_TYPE |
"text/xml" |
| gov.llnl.ontology.mapreduce.table.WordNetEvidenceTable | ||
|---|---|---|
public static final String |
ALL_CORPORA |
"" |
public static final String |
CLASS_CF |
"class" |
public static final String |
CLUSTER_SIMILARITY |
"cluster" |
public static final String |
COSINE_SIMILARITY |
"cosine" |
public static final String |
COUSIN_EVIDENCE |
"cousinEvidence" |
public static final String |
DEPENDENCY_FEATURE_CF |
"dependencyFeatures" |
public static final String |
DEPENDENCY_PATH_ANNOTATION_NAME |
"DependencyPathCounts" |
public static final String |
EUCLIDEAN_SIMILARITY |
"euclidean" |
public static final String |
HYPERNYM_EVIDENCE |
"hypernymEvidenceStatus" |
public static final String |
KL_SIMILARITY |
"kl_divergence" |
public static final String |
LIN_SIMILARITY |
"lin" |
public static final String |
LSH_CLUSTER_SIMILARITY |
"lsh" |
public static final String |
NOUN_PAIR_CF |
"nounPair" |
public static final String |
NOUN_PAIR_COLUMN |
"key" |
public static final String |
SIMILARITY_CF |
"similarity" |
public static final String |
TABLE_NAME |
"WordNetEvidence" |
| gov.llnl.ontology.text.corpora.NYTCorpusDocument | ||
|---|---|---|
public static final String |
CORPUS_NAME |
"NYT" |
| gov.llnl.ontology.text.corpora.NYTDocumentReader | ||
|---|---|---|
public static final String |
DATE_PUBLICATION_ATTRIBUTE |
"date.publication" |
| gov.llnl.ontology.text.corpora.SemEval2010TestDocumentReader | ||
|---|---|---|
public static final String |
CORPUS_NAME |
"semeval2010_test" |
| gov.llnl.ontology.text.corpora.SemEval2010TrainDocumentReader | ||
|---|---|---|
public static final String |
CORPUS_NAME |
"semeval2010_train" |
| gov.llnl.ontology.text.corpora.SenseEval2007DocumentReader | ||
|---|---|---|
public static final String |
CORPUS_NAME |
"senseEval2007" |
| gov.llnl.ontology.text.corpora.UkWacDocumentReader | ||
|---|---|---|
public static final String |
CORPUS_NAME |
"ukwac" |
| gov.llnl.ontology.text.corpora.WackypediaDocumentReader | ||
|---|---|---|
public static final String |
CORPUS_NAME |
"wackypedia" |
| gov.llnl.ontology.text.hbase.XMLRecordReader | ||
|---|---|---|
public static final String |
CONF_PREFIX |
"gov.llnl.ontology.text.hbase.XMLRecordReader" |
public static final String |
DELIMITER_TAG |
"gov.llnl.ontology.text.hbase.XMLRecordReader.tag" |
| gov.llnl.ontology.text.parse.MaltLinearParser | ||
|---|---|---|
public static final String |
PARSER_MODEL |
"engmalt.linear" |
| gov.llnl.ontology.text.parse.MaltSvmParser | ||
|---|---|---|
public static final String |
PARSER_MODEL |
"engmalt.poly" |
| gov.llnl.ontology.text.parse.StanfordParser | ||
|---|---|---|
public static final String |
PARSER_MODEL |
"models/stanford/englishPCFG.ser.gz" |
| gov.llnl.ontology.text.sentsplit.OpenNlpMESentenceSplitter | ||
|---|---|---|
public static final String |
DEFAULT_MODEL |
"models/OpenNLP/en-sent.bin" |
| gov.llnl.ontology.text.tag.OpenNlpMEPOSTagger | ||
|---|---|---|
public static final String |
DEFAULT_MODEL |
"models/OpenNLP/en-pos-maxent.bin" |
| gov.llnl.ontology.text.tokenize.OpenNlpMETokenizer | ||
|---|---|---|
public static final String |
DEFAULT_MODEL |
"models/OpenNLP/en-token.bin" |
| gov.llnl.ontology.wordnet.SynsetPagerank | ||
|---|---|---|
public static final String |
TRANSITION_ATTRIBUTE |
"transitionAttribute" |
| gov.llnl.ontology.wordnet.wsd.PageRankCentralityDisambiguation | ||
|---|---|---|
public static final String |
LINK |
"relation" |
| gov.llnl.ontology.wordnet.wsd.PersonalizedPageRankWSD | ||
|---|---|---|
public static final String |
LINK |
"related" |
|
||||||||||
| PREV NEXT | FRAMES NO FRAMES | |||||||||