úÎeñ_v_      !"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWX Y Z [ \ ] ^ None PNET entry. Trigger type. 3Does entry represents a trigger of the given type? )Parse dictionary into a list of entries. Read dictionary from the file.  _ `     _ ` NoneA < is a map from forms to labels. Each form may be annotated J with multiple labels. The map is represented using the directed acyclic  word graph. " type Dict = D.DAWG (S.Set Label) Dictionary label. .A Named Entity entry from the LMF dictionary. Orthographic form of the NE Type of the NE A orthographic form. A type of named entity. Is the form a multiword one? *Construct dictionary from the list of form/ label pairs. /Construct dictionary from the list of entries. >Remove dictionary entries which do not satisfy the predicate. !Save the dictionary in the file. #Load the dictionary from the file. Merge dictionary resources. a8Replacement implementation of unionsWith while there is $ no such function in dawg library. b7Replacement implementation of unionWith while there is $ no such function in dawg library. 6Differentiate labels from separate dictionaries using  dictionary-unique prefixes. c%Map function over the DAWG elements. dMap function over the set. eAdd integer prefix. abcdeabcdeNone-Parse the dictionary to the list of entries. #Read the dictionary from the file. fghij   fghij None!,Parse the NELexicon into a list of entries. "#Read the dictionary from the file. !k"!"!"!k"None#)Parse dictionary into a list of entries. $#Read the dictionary from the file. #l$#$#$#l$NonemIs it a single word entry? %"Extract NEs dictionary from PNEG. &'Extract NEs dictionary from NELexicon. '&Extract NEs dictionary from PoliMorf. ((Extract NEs dictionary from Prolexbase. )0Extract internal triggers from PNET dictionary. *0Extract external triggers from PNET dictionary. m%Path to PNEG in the LMF format &Path to NELexicon 'Path to PoliMorf (Path to Prolexbase ) Path to PNET * Path to PNET n%&'()*'%&()*m%&'()*nNone+AA label is created by encoding the named entity forest using the  IOB method. ,@An observation consist of an index (of list type) and an actual  observation value. -A named entity. .A word. +,-.+,-..-,++,-.None*/EConfiguration of the schema. All configuration elements specify the L range over which a particular observation type should be taken on account.  For example, the  [-1, 0, 2]- range means that observations of particular 2 type will be extracted with respect to previous (k - 1 ), current (k)  and after the next (k + 2-) positions when identifying the observation  set for position k in the input sentence. 1The H schema block. 2The I schema block. 3The J' schema block. The first list of ints ! represents lengths of prefixes. 4The K' schema block. The first list of ints ! represents lengths of suffixes. 5The L schema block. 6The M schema block. 7The N schema block. 8The O schema block. 9The P schema block. :Dictionaries of NEs (Q schema block). ;!Dictionary of internal triggers. <!Dictionary of external triggers. = Maybe entry. >Body of configuration entry. @&Range argument for the schema block. A+Additional arguments for the schema block. B>A block is a chunk of the Ox computation performed within the F context of the sentence and the list of absolute sentence positions. o1Record structure of the basic observation types. C?A schema is a block of the Ox computation performed within the = context of the sentence and the absolute sentence position. DCThe Ox monad specialized to word token type and text observations. EA dummy schema block. FHSequence the list of schemas (or blocks) and discard individual values. pConstruct the o structure given the sentence. G;Transform the block to the schema depending on the list of  relative sentence positions. H+Orthographic form at the current position. IGOrthographic form split into two observations: the lowercased form and B the original form (only when different than the lowercased one). J.List of lowercased prefixes of given lengths. K.List of lowercased suffixes of given lengths. L@Lemma substitute parametrized by the number specifying the span 5 over which lowercased prefixes and suffixes will be qd.  For example, lemmaB 2 will take affixes of lengths 0, -1 and -2  on account. MShape of the word. NPacked shape of the word. O'Combined shapes of two consecutive (at k-1 and k positions) words. P.Combined packed shapes of two consecutive (at k-1 and k positions)  words. Q?Plain dictionary search determined with respect to the list of  relative positions. R!Entry with additional arguemnts. r'Maybe entry with additional arguemnts. S*Plain entry with no additional arugments. T.Null configuration of the observation schema. U1Default configuration of the observation schema. V-Build the schema based on the configuration. W:Use the schema to extract observations from the sentence. 4/0123456789:;<=>?@ABostuCDEFpGHIJKLMNOPQRrSTUNamed Entity dictionaries  Dictionary of internal triggers  Dictionary of external triggers vwxVWyz)/0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVW)DCEFW>?@A=SR/0123456789:;<TUVBGHIJKLMNOPQ!/ 0123456789:;<=>?@ABostuCDEFpGHIJKLMNOPQRrSTUvwxVWyz NoneXKA Nerf consists of the observation schema configuration and the CRF model. \AShow results of observation extraction on the input ENAMEX file. ]3Train Nerf on the input data using the SGD method. ^7Perform named entity recognition (NER) using the Nerf. XYZ[{|}\] Args for SGD !Observation schema configuration Train data (ENAMEX) Maybe eval data (ENAMEX) $Nerf with resulting codec and model ^~ +,-.XYZ[\]^XYZ[]^\XYZ[{|}\]^~        !"#$%&'()*+,-./01234566789:;<=>?@AB CCDEFGHIJKLMNOPQRSTUVWXYZ[ \ \ ] ^ _ ` abcdefghijklmccnopqrstup vwxyz{ | } ~ € nerf-0.2.2NLP.Nerf.Dict.PNETNLP.Nerf.Dict.BaseNLP.Nerf.Dict.PNEGNLP.Nerf.Dict.NELexiconNLP.Nerf.Dict.Prolexbase NLP.Nerf.DictNLP.Nerf.TypesNLP.Nerf.SchemaNLP.NerfEntryorthbasetagtypneTypexampleTypExternalInternalhasTyp parsePNETreadPNETDictDAWGLabelneOrthneTypeFormNeType isMultiWord fromPairs fromEntriessiftDictsaveDictloadDictmergediff parsePNEGreadPNEGparseNELexicon readNELexiconparseProlexbasereadProlexbase extractPNEGextractNELexiconextractPoliMorfextractProlexbaseextractIntTriggersextractExtTriggersLbObNEWord SchemaConforthC splitOrthC lowPrefixesC lowSuffixesClemmaCshapeCpackedC shapePairC packedPairCdictC intTrigsC extTrigsCBodyrangeargsBlockSchemaOxvoid sequenceS_ fromBlockorthB splitOrthB lowPrefixesB lowSuffixesBlemmaBshapeBpackedB shapePairB packedPairBdictB entryWithentrynullConf defaultConffromConf schematizeNerf schemaConfcrftryOxtrainnerreadTyp parseLine unionsWith unionWithmapDmapS addPrefixlmfP lexEntryPwordPsensePfeatPatomic mkTriggersBaseObmkBaseObmonad-ox-0.2.0Control.Monad.Oxsave entryWith'MblowOrthmkArg0mkArg1mkArgs1$fBinarySchemaConf $fBinaryBodyflattenreadFlatdrawSent $fBinaryNerf