Commit b3d13d65 authored by Alexandre Delanoë's avatar Alexandre Delanoë

[NGRAMS] mono without corenlp.

parent e7e89297
Pipeline #214 failed with stage
......@@ -219,7 +219,7 @@ extractNgramsT doc = do
let institutes = map text2ngrams $ maybe ["Nothing"] (map toSchoolName . (splitOn ", ")) $ _hyperdataDocument_institutes doc
let authors = map text2ngrams $ maybe ["Nothing"] (splitOn ", ") $ _hyperdataDocument_authors doc
let leText = catMaybes [_hyperdataDocument_title doc, _hyperdataDocument_abstract doc]
terms' <- map text2ngrams <$> map (intercalate " " . _terms_label) <$> concat <$> liftIO (extractTerms (Multi EN) leText)
terms' <- map text2ngrams <$> map (intercalate " " . _terms_label) <$> concat <$> liftIO (extractTerms (Mono EN) leText)
pure $ DM.fromList $ [(source, DM.singleton Sources 1)]
<> [(i', DM.singleton Institutes 1) | i' <- institutes ]
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment