DeepTC - An extension of DKPro text classification for fostering reproducibility of deep learning experiments

Autor: Horsmann, Tobias, Zesch, Torsten

We present a deep learning extension for the multi-purpose text classification framework DKPro Text Classification (DKPro TC). DKProTC is a flexible framework for creating easily shareable and reproducible end-to-end NLP experiments involving machine

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::449a9bb3bb3b6555a690bf56e68e2ab2
https://www.scopus.com/inward/record.url?partnerID=HzOxMe3b&origin=inward&scp=85059893023

Method of determining keywords for English texts based on DKPro Core

Publikováno v: Technology audit and production reserves; Том 1, № 2(21) (2015): Information technology; 26-30
Technology audit and production reserves; Том 1, № 2(21) (2015): Інформаційні технології; 26-30
Technology audit and production reserves; Том 1, № 2(21) (2015): Информационные технологии; 26-30

Розглянуто підходи до пошуку ключових слів тексту, що грають важливу роль в задачах комп’ютерної лінгвістики. Запропоновано новий мето

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=scientific_p::a97a179c6d7c1b837a4412fc1b510fe9
http://journals.uran.ua/tarp/article/view/37274

Method of determining keywords for English texts based on DKPro Core

Publikováno v: Tehnologìčnij Audit ta Rezervi Virobnictva, Vol 1, Iss 2(21), Pp 26-30 (2015)

The approaches to search of keywords in text that are divided into two linguistic and statistical categories are considered. Linguistic methods are based on the meaning of words, especially using ontologies and semantic information of words. Unfortun

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1cbf8ccebcf42cad1600b0a63a110426
https://doi.org/10.15587/2312-8372.2015.37274

Method of determining of keywords in English texts based on the DKPro Core

Autor: Alexander Yahimovich, Ainur Kozbakova, Oleg Bisikalo, Saule Smailova, Waldemar Wójcik

Publikováno v: Photonics Applications in Astronomy, Communications, Industry, and High-Energy Physics Experiments 2016.

The new method of the keywords determining based on finding the connections between word forms of the English text with the instrumental capabilities of package DKPro Core is suggested in this article. The method, which is illustrated with examples o

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::173b701af351d97e608451c002feb067
https://doi.org/10.1117/12.2249225

DKPro Keyphrases: Flexible and Reusable Keyphrase Extraction Experiments

Autor: Iryna Gurevych, Nicolai Erbs, Pedro Santos, Torsten Zesch

Publikováno v: ACL (System Demonstrations)

DKPro Keyphrases is a keyphrase extraction framework based on UIMA. It offers a wide range of state-of-the-art keyphrase experiments approaches. At the same time, it is a workbench for developing new extraction approaches and evaluating their impact.

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a6c57734f0e6bec0cd3a3ac1a692f3c1
https://doi.org/10.3115/v1/p14-5006