Current simultaneous speech translation models can process audio only up...
Blockwise self-attentional encoder models have recently emerged as one
p...
Many meetings require creating a meeting summary to keep everyone up to ...
We explore the effectiveness of character-level neural machine translati...
This paper explores negative lexical constraining in English to Czech ne...
Whisper is one of the recent state-of-the-art multilingual speech recogn...
Many NLP tasks require to automatically identify the most significant wo...
We propose a genetic algorithm (GA) based method for modifying n-best li...
This paper presents HaVQA, the first multimodal dataset for visual
quest...
Automatic speech translation is sensitive to speech recognition errors, ...
The Shannon game has long been used as a thought experiment in linguisti...
We present the CUNI-Bergamot submission for the WMT22 General translatio...
There have been several studies on the correlation between human ratings...
In the cascaded approach to spoken language translation (SLT), the ASR o...
It is unclear whether, how and where large pre-trained language models
c...
Summarization is a challenging problem, and even more challenging is to
...
Multi-modal Machine Translation (MMT) enables the use of visual informat...
In this paper, we describe our submission to the Simultaneous Speech
Tra...
Eye-Tracking data is a very useful source of information to study cognit...
We present the Eyetracked Multi-Modal Translation (EMMT) corpus, a datas...
Neural sequence-to-sequence automatic speech recognition (ASR) systems a...
In simultaneous speech translation, one can vary the size of the output
...
Our book "The Reality of Multi-Lingual Machine Translation" discusses th...
This paper describes Charles University submission for Multilingual
Low-...
This paper describes Charles University submission for Terminology
trans...
Transformer-based sequence-to-sequence architectures, while achieving
st...
We test the natural expectation that using MT in professional translatio...
End-to-end neural automatic speech recognition systems achieved recently...
Lexically constrained machine translation allows the user to manipulate ...
Interpreters facilitate multi-lingual meetings but the affordable set of...
Existing models of multilingual sentence embeddings require large parall...
Translating text into a language unknown to the text's author, dubbed
ou...
We present the first version of a system for interactive generation of
t...
Being able to predict the length of a scientific paper may be helpful in...
This paper presents a description of CUNI systems submitted to the WMT20...
This work presents our ongoing research of unsupervised pretraining in n...
Some methods of automatic simultaneous translation of a long-form speech...
We present a new release of the Czech-English parallel corpus CzEng 2.0
...
We present THEaiTRE, a starting project aimed at automatic generation of...
Automatic methods and metrics that assess various quality criteria of
au...
This paper is an ELITR system submission for the non-native speech
trans...
Automatic evaluation of various text quality criteria produced by data-d...
Recent developments in sequence-to-sequence learning with neural network...
We present COSTRA 1.0, a dataset of complex sentence transformations. Th...
It is not uncommon for Internet users to have to produce text in a forei...
The utility of linguistic annotation in neural machine translation seeme...
Extractive keyphrase generation research has been around since the ninet...
We present an introductory investigation into continuous-space vector
re...
Neural machine translation is demanding in terms of training time, hardw...
Using data-driven models for solving text summarization or similar tasks...