Before using the service, please read the preliminary information containing a description of steps that enable access to the CLARIN-PL developer interface.
LEM (Literary Exploratory Machine) extracts statistical data from Polish literary texts. It allows for processing large text files.
The service calls selected tasks of the services provided by CLARIN-PL and saves the output data in an Excel file
[["any2txt","postagger"],{"statconverter":{"mode":"pos_determ"}}]Verbs characteristics
Words & part-of-speech statistics
Sentences & tokens statistics
[["any2txt","postagger"],{"statconverter":{"mode":"sent_token_stats"}}]Named entities determination
[["any2txt","keytool"],{"statconverter":{"mode":"ne_determ"}}]Named entities statistics
[["any2txt",{"postagger":{"method":"ner"}}],{"statconverter":{"mode":"ne_stats"}}]Entities relations
the task uses NER in Postagger
LPMN query: [["any2txt",{"postagger":{"method":"ner"}}],{"statconverter":{"mode": "ent_relations"}}]
form options:
limit - the maximum number of identified entities: by default 2000,window - sentence relations: by default 5,ann_type_options - entity type:
nam_liv - personnam_loc - placenam_org - organizationEntity relation extraction. Output format GEXF (Gephi).
Lemmatization
[["any2txt",{"postagger":{"output":"lemmas"}}]]Conversion to text
[["any2txt"]]Determining emotions and sentiment
[["any2txt",{"emotagger":{"mode":"sentence"}}],{"statconverter":{"mode":"emotagger"}}]The service can be run:
In Colab: LEM - Literary text exploration tasks
Maciej Maryl, Maciej Piasecki, Tomasz Walkowiak (2017) Literary Exploration Machine A Web-Based Application for Textual Scholars, Selected papers from the CLARIN Annual Conference 2017. Linköping Electronic Conference Proceedings 147, Budapest, 128-144.
(C) CLARIN-PL