src/Gargantext/Core/Text.hs

   1 {-|
   2 Module      : Gargantext.Core.Text
   3 Description : Ngrams tools
   4 Copyright   : (c) CNRS, 2018
   5 License     : AGPL + CECILL v3
   6 Maintainer  : team@gargantext.org
   7 Stability   : experimental
   8 Portability : POSIX
   9
  10 Text gathers terms in unit of contexts.
  11
  12 -}
  13
  14
  15 module Gargantext.Core.Text
  16   where
  17
  18 import Data.Text (Text, split)
  19 import Gargantext.Prelude hiding (filter)
  20 import NLP.FullStop (segment)
  21 import qualified Data.Text as DT
  22
  23 -----------------------------------------------------------------
  24 class HasText h
  25   where
  26     hasText :: h -> [Text]
  27
  28 -----------------------------------------------------------------
  29 -- French words to distinguish contexts
  30 newtype Texte      = Texte      Text
  31 newtype Paragraphe = Paragraphe Text
  32 newtype Phrase     = Phrase     Text
  33 newtype MultiTerme = MultiTerme Text
  34 newtype Mot        = Mot        Text
  35 newtype Lettre     = Lettre     Text
  36
  37 -- | Type syn seems obvious
  38 type    Titre      = Phrase
  39
  40 -----------------------------------------------------------------
  41
  42 instance Show Texte where
  43   show (Texte t) = show t
  44
  45 instance Show Paragraphe where
  46   show (Paragraphe p) = show p
  47
  48 instance Show Phrase where
  49   show (Phrase p) = show p
  50
  51 instance Show MultiTerme where
  52   show (MultiTerme mt) = show mt
  53
  54 instance Show Mot where
  55   show (Mot t) = show t
  56
  57 instance Show Lettre where
  58   show (Lettre l) = show l
  59
  60 -----------------------------------------------------------------
  61
  62 class Collage sup inf where
  63   dec ::  sup  -> [inf]
  64   inc :: [inf] -> sup
  65
  66 instance Collage Texte Paragraphe where
  67   dec (Texte t) = map Paragraphe $ DT.splitOn "\n" t
  68   inc           = Texte . DT.intercalate "\n" . map (\(Paragraphe t) -> t)
  69
  70 instance Collage Paragraphe Phrase where
  71   dec (Paragraphe t) = map Phrase $ sentences t
  72   inc                = Paragraphe . DT.unwords . map (\(Phrase p) -> p)
  73
  74 instance Collage Phrase MultiTerme where
  75   dec (Phrase t) = map MultiTerme $ DT.words t
  76   inc            = Phrase . DT.unwords . map (\(MultiTerme p) -> p)
  77
  78 instance Collage MultiTerme Mot where
  79   dec (MultiTerme mt) = map Mot $ DT.words mt
  80   inc                 = MultiTerme . DT.intercalate " " . map (\(Mot m) -> m)
  81
  82 -------------------------------------------------------------------
  83 -- Contexts of text
  84 sentences :: Text -> [Text]
  85 sentences txt = map DT.pack $ segment $ DT.unpack txt
  86
  87 sentences' :: Text -> [Text]
  88 sentences' txt = split isCharStop txt
  89
  90 isCharStop :: Char -> Bool
  91 isCharStop c = c `elem` ['.','?','!']
  92
  93 unsentences :: [Text] -> Text
  94 unsentences txts = DT.intercalate " " txts
  95
  96 -- | https://en.wikipedia.org/wiki/Text_mining
  97 testText_en :: Text
  98 testText_en = DT.pack "Text mining, also referred to as text data mining, roughly equivalent to text analytics, is the process of deriving high-quality information from text. High-quality information is typically derived through the devising of patterns and trends through means such as statistical pattern learning. Text mining usually involves the process of structuring the input text (usually parsing, along with the addition of some derived linguistic features and the removal of others, and subsequent insertion into a database), deriving patterns within the structured data, and finally evaluation and interpretation of the output. 'High quality' in text mining usually refers to some combination of relevance, novelty, and interestingness. Typical text mining tasks include text categorization, text clustering, concept/entity extraction, production of granular taxonomies, sentiment analysis, document summarization, and entity relation modeling (i.e., learning relations between named entities). Text analysis involves information retrieval, lexical analysis to study word frequency distributions, pattern recognition, tagging/annotation, information extraction, data mining techniques including link and association analysis, visualization, and predictive analytics. The overarching goal is, essentially, to turn text into data for analysis, via application of natural language processing (NLP) and analytical methods. A typical application is to scan a set of documents written in a natural language and either model the document set for predictive classification purposes or populate a database or search index with the information extracted."
  99
 100
 101 testText_en_2 :: Text
 102 testText_en_2 = DT.pack "It is hard to detect important articles in a specific context. Information retrieval techniques based on full text search can be inaccurate to identify main topics and they are not able to provide an indication about the importance of the article. Generating a citation network is a good way to find most popular articles but this approach is not context aware. The text around a citation mark is generally a good summary of the referred article. So citation context analysis presents an opportunity to use the wisdom of crowd for detecting important articles in a context sensitive way. In this work, we analyze citation contexts to rank articles properly for a given topic. The model proposed uses citation contexts in order to create a directed and edge-labeled citation network based on the target topic. Then we apply common ranking algorithms in order to find important articles in this newly created network. We showed that this method successfully detects a good subset of most prominent articles in a given topic. The biggest contribution of this approach is that we are able to identify important articles for a given search term even though these articles do not contain this search term. This technique can be used in other linked documents including web pages, legal documents, and patents as well as scientific papers."
 103
 104
 105 -- | https://fr.wikipedia.org/wiki/Fouille_de_textes
 106 testText_fr :: Text
 107 testText_fr = DT.pack "La fouille de textes ou « l'extraction de connaissances » dans les textes est une spécialisation de la fouille de données et fait partie du domaine de l'intelligence artificielle. Cette technique est souvent désignée sous l'anglicisme text mining. Elle désigne un ensemble de traitements informatiques consistant à extraire des connaissances selon un critère de nouveauté ou de similarité dans des textes produits par des humains pour des humains. Dans la pratique, cela revient à mettre en algorithme un modèle simplifié des théories linguistiques dans des systèmes informatiques d'apprentissage et de statistiques. Les disciplines impliquées sont donc la linguistique calculatoire, l'ingénierie des langues, l'apprentissage artificiel, les statistiques et l'informatique."
 108
 109 termTests :: Text
 110 termTests = "It is hard to detect important articles in a specific context. Information retrieval techniques based on full text search can be inaccurate to identify main topics and they are not able to provide an indication about the importance of the article. Generating a citation network is a good way to find most popular articles but this approach is not context aware. The text around a citation mark is generally a good summary of the referred article. So citation context analysis presents an opportunity to use the wisdom of crowd for detecting important articles in a context sensitive way. In this work, we analyze citation contexts to rank articles properly for a given topic. The model proposed uses citation contexts in order to create a directed and edge-labeled citation network based on the target topic. Then we apply common ranking algorithms in order to find important articles in this newly created network. We showed that this method successfully detects a good subset of most prominent articles in a given topic. The biggest contribution of this approach is that we are able to identify important articles for a given search term even though these articles do not contain this search term. This technique can be used in other linked documents including web pages, legal documents, and patents as well as scientific papers."
 111
 112
 113 -- | Ngrams Test
 114 -- >> ngramsTest testText
 115 -- 248
 116 --ngramsTest :: Text -> Int
 117 --ngramsTest x =  length ws
 118 --  where
 119 --    --txt = concat <$> lines <$> clean <$> readFile filePath
 120 --    txt = clean x
 121 --    -- | Number of sentences
 122 --    --ls   = sentences $ txt
 123 --    -- | Number of monograms used in the full text
 124 --    ws   = ngrams    $ txt
 125 --    -- | stem ngrams
 126     -- TODO
 127     -- group ngrams
 128     --ocs  = occ       $ ws
 129
 130 -- | Ngrams size
 131 size :: Text -> Int
 132 size t = 1 + DT.count " " t
 133
 134
 135