Multi-word Expressions for Abusive Speech Detection in Serbian

no code implementations • COLING (MWE) 2020 • Ranka Stanković, Jelena Mitrović, Danka Jokić, Cvetana Krstev

This paper presents our work on the refinement and improvement of the Serbian language part of Hurtlex, a multilingual lexicon of words to hurt.

Abusive Language

Sentiment Analysis of Serbian Old Novels

no code implementations • SALLD (LREC) 2022 • Ranka Stanković, Miloš Košprdić, Milica Ikonić Nešić, Tijana Radović

Set of sentences for SA was extracted from 120 novels of Serbian part of ELTeC collection, labelled for polarity and used for several model training.

LEMMA POS +2

From ELTeC Text Collection Metadata and Named Entities to Linked-data (and Back)

no code implementations • LDL (ACL) 2022 • Milica Ikonić Nešić, Ranka Stanković, Christof Schöch, Mihailo Skoric

In this paper we present the wikification of the ELTeC (European Literary Text Collection), developed within the COST Action “Distant Reading for European Literary History” (CA16204).

Entity Linking named-entity-recognition +3

Serbian NER&Beyond: The Archaic and the Modern Intertwinned

no code implementations • RANLP 2021 • Branislava Šandrih Todorović, Cvetana Krstev, Ranka Stanković, Milica Ikonić Nešić

In this work, we present a Serbian literary corpus that is being developed under the umbrella of the “Distant Reading for European Literary History” COST Action CA16204.

NER

Distant Reading in Digital Humanities: Case Study on the Serbian Part of the ELTeC Collection

no code implementations • LREC 2022 • Ranka Stanković, Cvetana Krstev, Branislava Šandrih Todorović, Dusko Vitas, Mihailo Skoric, Milica Ikonić Nešić

In this paper we present the Serbian part of the ELTeC multilingual corpus of novels written in the time period 1840-1920.

Lemmatization named-entity-recognition +5