539 research outputs found
Sort by
ParCzech 3.0: A Large Czech Speech Corpus with Rich Metadata
No full textWe present ParCzech 3.0, a speech corpus of the Czech parliamentary speeches from The Czech Chamber of Deputies which took place from 25th November 2013 to 1st April 2021.
Different from previous speech corpora of Czech, we preserve not just orthography but also all the available metadata (speaker identities, gender, web pages links, affiliations committees, political groups, etc.) and complement this with automatic morphological and syntactic annotation, and named entities recognition. The corpus is encoded in the TEI format which allows for a straightforward and versatile exploitation.
The rather rich metadata and annotation make the corpus relevant for a~wide audience of researchers ranging from engineers in the speech community to theoretical linguists studying rhetorical patterns at scale
End-to-End Lexically Constrained Machine Translation for Morphologically Rich Languages
No full textLexically constrained machine translation allows the user to manipulate the output sentence by enforcing the presence or absence of certain words and phrases. Although current approaches can enforce terms to appear in the translation, they often struggle to make the constraint word form agree with the rest of the generated output. Our manual analysis shows that 46% of the errors in the output of a baseline constrained model for English to Czech translation are related to agreement. We investigate mechanisms to allow neural machine translation to infer the correct word inflection given lemmatized constraints. In particular, we focus on methods based on training
the model with constraints provided as part of the input sequence. Our experiments on the English-Czech language pair show that this approach improves the translation of constrained
terms in both automatic and manual evaluation
by reducing errors in agreement. Our approach
thus eliminates inflection errors, without introducing new errors or decreasing the overall
quality of the translation
SLTev: Comprehensive Evaluation of Spoken Language Translation
No full textAutomatic evaluation of Machine Translation(MT) quality has been investigated over several decades. Spoken Language Translation (SLT), especially when simultaneous, needs to consider additional criteria and does not have a standard evaluation procedure and a widely used toolkit. To fill the gap, we introduce SLTev, an open-source tool for assessing SLT in a comprehensive way. SLTev reports the quality, latency, and stability of an SLT candidate output based on the time-stamped transcript and reference translation into a target language. For quality, we rely on sacreBLEU which provides MT evaluation measures such as chrF or BLEU. For latency, we propose two new scoring techniques. For stability, we extend the previously defined measures with a normalized Flicker in our work. We also propose a new averaging of older measures. A preliminary version of SLTev was used in the IWSLT 2020 SHARED TASK. Moreover, a growing collection of test datasets directly accessible by SLTev are provided for system evaluation comparable across papers
Lost in Interpreting: Speech Translation from Source or Interpreter?
No full textInterpreters facilitate multi-lingual meetings but the affordable set of languages is often smaller than what is needed. Automatic simultaneous speech translation can extend the set of provided languages. We investigate if such an automatic system should rather follow the original speaker, or an interpreter to achieve better translation quality at the cost of increased delay.
To answer the question, we release Europarl Simultaneous Interpreting Corpus (ESIC), 10 hours of recordings and transcripts of European Parliament speeches in English, with simultaneous interpreting into Czech and German. We evaluate quality and latency of speaker-based and interpreter-based spoken translation systems from English to Czech. We study the differences in implicit simplification and summarization of the human interpreter compared to a machine translation system trained to shorten the output to some extent. Finally, we perform human evaluation to measure information loss of each of these approaches
CUNI systems for WMT21: Multilingual Low-Resource Translation for Indo-European Languages Shared Task
No full textThis paper describes Charles University submission for Multilingual Low-Resource Translation for Indo-European Languages shared task at WMT21. We competed in translation from Catalan into Romanian, Italian and Occitan. Our systems are based on shared multilingual model. We show that using joint model for multiple similar language pairs improves upon translation quality in each pair. We also demonstrate that chararacter-level bilingual models are competitive for very similar language pairs (Catalan-Occitan) but less so for more distant pairs. We also describe our experiments with multi-task learning, where aside from a textual translation, the models are also trained to perform grapheme-to-phoneme conversion
MTEQA at WMT21 Metrics Shared Task
No full textIn this paper, we describe our submission to the WMT 2021 Metrics Shared Task. We use the automatically-generated questions and answers to evaluate the quality of Machine Translation (MT) systems. Our submission builds upon the recently proposed MTEQA framework. Experiments on WMT20 evaluation datasets show that at the system-level the MTEQA metric achieves performance comparable with other state-of-the-art solutions, while considering only a certain amount of information from the whole translation
WMT21 Marian translation model (ca-oc)
No full textMarian NMT model for Catalan to Occitan translation. The model was submitted to WMT'21 Shared Task on Multilingual Low-Resource Translation for Indo-European Languages as a CUNI-Primary system for Catalan to Occitan
European Language Grid: A Joint Platform for the European Language Technology Community
No full textEurope is a multilingual society, in which dozens of languages are spoken. The only option to enable and to benefit from multilingualism is through Language Technologies (LT), i.e., Natural Language Processing and Speech Technologies. We describe the European Language Grid (ELG), which is targeted to evolve into the primary platform and marketplace for LT in Europe by providing one umbrella platform for the European LT landscape, including research and industry, enabling all stakeholders to upload, share and distribute their services, products and resources. At the end of our EU project, which will establish a legal entity in 2022, the ELG will provide access to approx. 1300 services for all European languages as well as thousands of data sets
Is one head enough? Mention heads in coreference annotations compared with UD-style heads
No full textWe present an empirical study that compares mention heads as annotated manually in four coreference datasets (for Dutch, English, Polish, and Russian) on one hand, with heads induced from dependency trees parsed automatically, on the other hand
D3.9 Report on Ontology and Vocabulary Collection and Publication
No full textThe deliverable presents three detailed case studies for each of the main topical areas of SSHOC Task 3.1 “Multilingual Terminologies'' aiming to investigate NLP and MT approaches in view of providing resources and tools to foster multilingual access to SSH content across different languages and improve discovery by non-native speakers. A set of multilingual metadata concepts, multilingual vocabularies and automatically extracted multilingual terminologies has been delivered as freely, openly available data, fully corresponding to the FAIR principles promoted within the EOSC, findable through the VLO and other CLARIN and SSHOC services