conftrace_

2023 EACL EACL 2023

Croatian Film Review Dataset (Cro-FiReDa): A Sentiment Annotated Dataset of Film Reviews

Abstract

AbstractThis paper introduces Cro-FiReDa, a sentiment-annotated dataset for Croatian in the domain of movie reviews. The dataset, which contains over 10,000 sentences, has been annotated at the sentence level. In addition to presentingthe overall annotation process, we also present benchmark results based on the transformer-based fine-tuning approach.

Authors

Gaurish Thakkar, Nives Mikelic Preradovic, Marko Tadić

Topics

Machine Learning > Core Methods > Classification Machine Learning > Core Methods > Representation Learning Deep Learning > Architectures > Transformers

Keywords

sentiment analysis transformer fine-tuning sentence-level annotation croatian language film review

More from EACL 2023

All EACL 2023 papers →

Named Entity Recognition for Low-Resource Languages - Profiting from Language Families

MAUPQA: Massive Automatically-created Polish Question Answering Dataset

TrelBERT: A pre-trained encoder for Polish Twitter

Too Many Cooks Spoil the Model: Are Bilingual Models for Slovene Better than a Large Multilingual Model?

Machine-translated texts from English to Polish show a potential for typological explanations in Source Language Identification

Comparing domain-specific and domain-general BERT variants for inferred real-world knowledge through rare grammatical features in Serbian