539 research outputs found
Sort by
Ptakopět data: the dataset for experiments on outbound translation
No full textThe dataset used for the Ptakopět experiment on outbound machine translation. It consists of screenshots of web forms with user queries entered. The queries are available also in a text form. The dataset comprises two language versions: English and Czech. Whereas the English version has been fully post-processed (screenshots cropped, queries within the screenshots highlighted, dataset split based on its quality etc.), the Czech version is raw as it was collected by the annotators
Strojové překlady a tlumočení
No full textA presentation for students of translation studies and interpretring
Towards a Versatile Intelligent Conversational Agent as Personal Assistant for Migrants
No full textWe present a knowledge-driven multilingual conversational agent (referred to as ``MyWelcome Agent'') that acts as personal assistant for migrants in the contexts of their reception and integration. In order to also account for tasks that go beyond communication and require advanced service coordination skills, the architecture of the proposed platform separates the dialogue management service from the agent behavior including the service selection and planning. The involvement of genuine agent planning strategies in the design of personal assistants, which tend to be limited to dialogue management tasks, makes the proposed agent significantly more versatile and intelligent. To ensure high quality verbal interaction, we draw upon state-of-the-art multilingual spoken language understanding and generation technologies
FINDINGS OF THE IWSLT 2021 EVALUATION CAMPAIGN
No full textThe evaluation campaign of the International
Conference on Spoken Language Translation
(IWSLT 2021) featured this year four shared
tasks: (i) Simultaneous speech translation, (ii)
Offline speech translation, (iii) Multilingual
speech translation, (iv) Low-resource speech
translation. A total of 22 teams participated
in at least one of the tasks. This paper de-
scribes each shared task, data and evaluation
metrics, and reports results of the received submissions
ELITR Demo at LCT Summer School
No full textI presented the research project ELITR and the state of the art in machine translation and speech translation
CorefUD 0.2
No full textCorefUD is a collection of previously existing datasets annotated with coreference, which we converted into a common annotation scheme. In total, CorefUD in its current version 0.2 consists of 17 datasets for 11 languages, and compared to the version 0.1, the automatic morpho-syntactic annotation has improved
Sequence Length is a Domain: Length-based Overfitting in Transformer Models
No full textTransformer-based sequence-to-sequence architectures, while achieving state-of-the-art results on a large number of NLP tasks, can still suffer from overfitting during training. In practice, this is usually countered either by applying regularization methods (e.g. dropout, L2-regularization) or by providing huge amounts of training data. Additionally, Transformer and other architectures are known to struggle when generating very long sequences. For example, in machine translation, the neural-based systems perform worse on very long sequences when compared to the preceding phrase-based translation approaches (Koehn and Knowles, 2017).
We present results which suggest that the issue might also be in the mismatch between the length distributions of the training and validation data combined with the aforementioned tendency of the neural networks to overfit to the training data. We demonstrate on a simple string editing task and a machine translation task that the Transformer model performance drops significantly when facing sequences of length diverging from the length distribution in the training data. Additionally, we show that the observed drop in performance is due to the hypothesis length corresponding to the lengths seen by the model during training rather than the length of the input sequence
Operating a Complex SLT System with Speakers and Human Interpreters
No full textThe paper describes the practical experience from testing our complex system translating from the speech of speakers and interpreters
Just Ask! Evaluating Machine Translation by Asking and Answering Questions
No full textIn this paper, we show that automatically-generated questions and answers can be used to evaluate the quality of Machine Translation systems. Building on recent work on the evaluation of abstractive text summarization, we propose a new metric for system-level Machine Translation evaluation, compare it with other state-of-the-art solutions, and show its robustness by conducting experiments for various translation directions
ELITR Multilingual Live Subtitling: Demo and Strategy
No full textThis paper presents an automatic speech translation system aimed at live subtitling of conference presentations. We describe the overall architecture and key processing components. More importantly, we explain our strategy for building a complex system for end-users from numerous individual components, each of which has been tested only in laboratory conditions. The system is a working prototype that is routinely tested in recognizing English, Czech, and German speech and presenting it translated simultaneously into 42 target languages