Výsledky vyhledávání - "Repar, Andraž"

Report

Evaluation of contextual embeddings on less-resourced languages

Autor: Ulčar, Matej, Žagar, Aleš, Armendariz, Carlos S., Repar, Andraž, Pollak, Senja, Purver, Matthew, Robnik-Šikonja, Marko

The current dominance of deep neural networks in natural language processing is based on contextual embeddings such as ELMo, BERT, and BERT derivatives. Most existing work focuses on English; in contrast, we present here the first multilingual empiri

Externí odkaz: http://arxiv.org/abs/2107.10614

Zobrazit plný text záznamu

Report

RaKUn: Rank-based Keyword extraction via Unsupervised learning and Meta vertex aggregation

Autor: Škrlj, Blaž, Repar, Andraž, Pollak, Senja

Publikováno v: Statistical Language and Speech Processing 2019 Proceedings

Keyword extraction is used for summarizing the content of a document and supports efficient document retrieval, and is as such an indispensable part of modern text-based systems. We explore how load centrality, a graph-theoretic measure applied to gr

Externí odkaz: http://arxiv.org/abs/1907.06458

Zobrazit plný text záznamu

Akademický článek

Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.

Word-embedding based bilingual terminology alignment

Autor: Repar, Andraž, Martinc, Matej, Ulčar, Matej, Pollak, Senja

The ability to accurately align concepts between languages can provide significant benefits in many practical applications. In this paper, we extend a machine learning approach using dictionary and cognate-based features with novel cross-lingual embe

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5f44adcf738f26899881bdb2b207ece0

Zobrazit plný text záznamu

Aligning Estonian and Russian news industry keywords with the help of subtitle translations and an environmental thesaurus

Autor: Repar, Andraž, Shumakov, Andrej

This paper presents the implementation of a bilingual term alignment approach developed by Repar et al. (2019) to a dataset of unaligned Estonian and Russian keywords which were manually assigned by journalists to describe the article topic. We start

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::50397792751b4aa503d5dd2ad4a86544
https://doi.org/10.5281/zenodo.4730392

Zobrazit plný text záznamu

Akademický článek

Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.

Replication, analysis and adaptation of a term alignment approach

Autor: Repar, Andraž, Martinc, Matej, Pollak, Senja

In this paper, we look at the issue of reproducibility and replicability in bilingual terminology alignment (BTA). We propose a set of best practices for reproducibility and replicability of NLP papers and analyze several influential BTA papers from

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=od______2659::721a495d91e4284da6f032cb3d671a51
https://zenodo.org/record/3559084

Zobrazit plný text záznamu

TermEnsembler: An enseble learning approach to bilingual term extraction and alignment

Autor: Repar, Andraž, Podpečan, Vid, Vavpetič, Anže, Lavrač, Nada, Pollak, Senja

This paper describes TermEnsembler, a bilingual term extraction and alignment system utilizing a novel ensemble learning approach to bilingual term alignment. In the proposed system, the processing starts with monolingual term extraction from a langu

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=od______2659::b64af9f5e30c61780493c74e5878e950
https://zenodo.org/record/3371071

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání