Search Results for author: Maja Popovi{\'c}

Found 31 papers, 2 papers with code

Relations between comprehensibility and adequacy errors in machine translation output

no code implementations CONLL 2020 Maja Popovi{\'c}

This work presents a detailed analysis of translation errors perceived by readers as comprehensibility and/or adequacy issues.

Machine Translation Translation +1

On Context Span Needed for Machine Translation Evaluation

no code implementations LREC 2020 Sheila Castilho, Maja Popovi{\'c}, Andy Way

Despite increasing efforts to improve evaluation of machine translation (MT) by going beyond the sentence level to the document level, the definition of what exactly constitutes a {``}document level{''} is still not clear.

Machine Translation Translation

Automated Text Simplification as a Preprocessing Step for Machine Translation into an Under-resourced Language

no code implementations RANLP 2019 Sanja {\v{S}}tajner, Maja Popovi{\'c}

We use the state-of-the-art automatic text simplification (ATS) system for lexically and syntactically simplifying source sentences, which are then translated with two state-of-the-art English-to-Serbian MT systems, the phrase-based MT (PBMT) and the neural MT (NMT).

Machine Translation NMT +2

Are ambiguous conjunctions problematic for machine translation?

no code implementations RANLP 2019 Maja Popovi{\'c}, Sheila Castilho

In total, we evaluate the conjunction {``}but{''} on 20 translation outputs, and the conjunction {``}and{''} on 10.

Machine Translation Translation

Building English-to-Serbian Machine Translation System for IMDb Movie Reviews

1 code implementation WS 2019 Pintu Lohar, Maja Popovi{\'c}, Andy Way

This paper reports the results of the first experiment dealing with the challenges of building a machine translation system for user-generated content involving a complex South Slavic language.

Machine Translation Translation

Evaluating Conjunction Disambiguation on English-to-German and French-to-German WMT 2019 Translation Hypotheses

no code implementations WS 2019 Maja Popovi{\'c}

Qualitative manual inspection of translation hypotheses shown that highly ranked systems generally produce translations with high adequacy and fluency, meaning that these systems are not only capable of capturing the right conjunction whereas the rest of the translation hypothesis is poor.

Translation

Complex Word Identification Using Character n-grams

no code implementations WS 2018 Maja Popovi{\'c}

The system was ranked in the middle range for all English texts, as third of fourteen submissions for German, and as tenth of seventeen submissions for Spanish.

Complex Word Identification Lexical Simplification +2

Language Related Issues for Machine Translation between Closely Related South Slavic Languages

no code implementations WS 2016 Maja Popovi{\'c}, Mihael Ar{\v{c}}an, Filip Klubi{\v{c}}ka

This work explores the obstacles for machine translation systems between closely related South Slavic languages, namely Croatian, Serbian and Slovenian.

Machine Translation Translation

PE2rr Corpus: Manual Error Annotation of Automatically Pre-annotated MT Post-edits

no code implementations LREC 2016 Maja Popovi{\'c}, Mihael Ar{\v{c}}an

We present a freely available corpus containing source language texts from different domains along with their automatically generated translations into several distinct morphologically rich languages, their post-edited versions, and error annotations of the performed post-edit operations.

Classification General Classification

The taraX\"U corpus of human-annotated machine translations

no code implementations LREC 2014 Eleftherios Avramidis, Aljoscha Burchardt, Sabine Hunsicker, Maja Popovi{\'c}, Cindy Tscherwinka, David Vilar, Hans Uszkoreit

Human translators are the key to evaluating machine translation (MT) quality and also to addressing the so far unanswered question when and how to use MT in professional translation workflows.

General Classification Machine Translation +1

Terra: a Collection of Translation Error-Annotated Corpora

no code implementations LREC 2012 Mark Fishel, Ond{\v{r}}ej Bojar, Maja Popovi{\'c}

Recently the first methods of automatic diagnostics of machine translation have emerged; since this area of research is relatively young, the efforts are not coordinated.

Machine Translation Translation

Automatic MT Error Analysis: Hjerson Helping Addicter

no code implementations LREC 2012 Jan Berka, Ond{\v{r}}ej Bojar, Mark Fishel, Maja Popovi{\'c}, Daniel Zeman

We present a complex, open source tool for detailed machine translation error analysis providing the user with automatic error detection and classification, several monolingual alignment algorithms as well as with training and test corpus browsing.

General Classification Machine Translation +1

Cannot find the paper you are looking for? You can Submit a new open access paper.