Search Results for author:
Found 101 papers, 24 papers with code
Operating a Complex SLT System with Speakers and Human Interpreters
We describe our experience with providing automatic simultaneous spoken language translation for an event with human interpreters.
CUNI Basque-to-English Submission in IWSLT18
We present our submission to the IWSLT18 Low Resource task focused on the translation from Basque-to-English.
Constrained Decoding for Technical Term Retention in English-Hindi MT
Technical terms may require special handling when the target audience is bilingual, depending on the cultural and educational norms of the society in question.
Results of the WMT21 Metrics Shared Task: Evaluating Metrics with Expert-based Human Evaluations on TED and News Domain
Contrary to previous years’ editions, this year we acquired our own human ratings based on expert-based human evaluation via Multidimensional Quality Metrics (MQM).
A Fine-Grained Analysis of BERTScore
BERTScore, a recently proposed automatic metric for machine translation quality, uses BERT, a large pre-trained language model to evaluate candidate translations with respect to a gold translation.
CUNI Systems in WMT21: Revisiting Backtranslation Techniques for English-Czech NMT
We use the latter for experiments with various backtranslation techniques.
Findings of the 2021 Conference on Machine Translation (WMT21)
This paper presents the results of the newstranslation task, the multilingual low-resourcetranslation for Indo-European languages, thetriangular translation task, and the automaticpost-editing task organised as part of the Con-ference on Machine Translation (WMT) 2021. In the news task, participants were asked tobuild machine translation systems for any of10 language pairs, to be evaluated on test setsconsisting mainly of news stories.
FINDINGS OF THE IWSLT 2021 EVALUATION CAMPAIGN
The 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.
Overview of the 8th Workshop on Asian Translation
This paper presents the results of the shared tasks from the 8th workshop on Asian translation (WAT2021).
Overview of the 9th Workshop on Asian Translation
This paper presents the results of the shared tasks from the 9th workshop on Asian translation (WAT2022).
ELITR Minuting Corpus: A Novel Dataset for Automatic Minuting from Multi-Party Meetings in English and Czech
Our dataset, AutoMin, consists of 113 (English) and 53 (Czech) meetings, covering more than 160 hours of meeting content.
Findings of the IWSLT 2022 Evaluation Campaign
The evaluation campaign of the 19th International Conference on Spoken Language Translation featured eight shared tasks: (i) Simultaneous speech translation, (ii) Offline speech translation, (iii) Speech to speech translation, (iv) Low-resource speech translation, (v) Multilingual speech translation, (vi) Dialect speech translation, (vii) Formality control for speech translation, (viii) Isometric speech translation.
Detecting Post-Edited References and Their Effect on Human Evaluation
This paper provides a quick overview of possible methods how to detect that reference translations were actually created by post-editing an MT system.
NLPHut’s Participation at WAT2021
Our submission tops in English→Malayalam Multimodal translation task (text-only translation, and Malayalam caption), and ranks second-best in English→Hindi Multimodal translation task (text-only translation, and Hindi caption).
ELITR: European Live Translator
ELITR (European Live Translator) project aims to create a speech translation system for simultaneous subtitling of conferences and online meetings targetting up to 43 languages.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
CUNI Submission to the BUCC 2022 Shared Task on Bilingual Term Alignment
We present our submission to the BUCC Shared Task on bilingual term alignment in comparable specialized corpora.
Multimodality for NLP-Centered Applications: Resources, Advances and Frontiers
With the development of multimodal systems and natural language generation techniques, the resurgence of multimodal datasets has attracted significant research interests, which aims to provide new information to enrich the representation of textual data.
UFAL Submissions to the IWSLT 2016 MT Track
We present our submissions to the IWSLT 2016 machine translation task, as our first attempt to translate subtitles and one of our early experiments with neural machine translation (NMT).
Results of the WMT20 Metrics Shared Task
Participants were asked to score the outputs of the translation systems competing in the WMT20 News Translation Task with automatic metrics.
WMT20 Document-Level Markable Error Exploration
For an annotation experiment of two phases, we chose Czech and English documents translated by systems submitted to WMT20 News Translation Task.
ODIANLP’s Participation in WAT2020
We have participated in the English-Hindi Multimodal task and Indic task.
Overview of the 7th Workshop on Asian Translation
This paper presents the results of the shared tasks from the 7th workshop on Asian translation (WAT2020).
How "Real" is Your Real-Time Simultaneous Speech-to-Text Translation System?
Simultaneous speech-to-text translation (SimulST) translates source-language speech into target-language text concurrently with the speaker's speech, ensuring low latency for better user comprehension.
Findings of the IWSLT 2024 Evaluation Campaign
This paper reports on the shared tasks organized by the 21st IWSLT Conference.
Adversarial Testing as a Tool for Interpretability: Length-based Overfitting of Elementary Functions in Transformers
The Transformer model has a tendency to overfit various aspects of the training data, such as the overall sequence length.
Evaluating the IWSLT2023 Speech Translation Tasks: Human Annotations, Automatic Metrics, and Segmentation
Human evaluation is a critical component in machine translation system development and has received much attention in text translation research.
Understanding the role of FFNs in driving multilingual behaviour in LLMs
In this paper, we conduct an in-depth analysis of the multilingual capabilities of a family of a Large Language Model, examining its architecture, activation patterns, and processing mechanisms across languages.
On Difficulties of Attention Factorization through Shared Memory
Transformers have revolutionized deep learning in numerous fields, including natural language processing, computer vision, and audio processing.
Quality and Quantity of Machine Translation References for Automatic Metrics
Automatic machine translation metrics typically rely on human translations to determine the quality of system translations.
Evaluating Optimal Reference Translations
The overall translation quality reached by current machine translation (MT) systems for high-resourced language pairs is remarkably good.
Boosting Unsupervised Machine Translation with Pseudo-Parallel Data
Even with the latest developments in deep learning and large-scale language modeling, the task of machine translation (MT) of low-resource languages remains a challenge.
Incremental Blockwise Beam Search for Simultaneous Speech Translation with Controllable Quality-Latency Tradeoff
Further, this method lacks mechanisms for \textit{controlling} the quality vs. latency tradeoff.
Minuteman: Machine and Human Joining Forces in Meeting Summarization
The tool provides a live transcript and a live meeting summary to the users, who can edit them in a collaborative manner, enabling correction of ASR errors and imperfect summary points in real time.
Character-level NMT and language similarity
We explore the effectiveness of character-level neural machine translation using Transformer architecture for various levels of language similarity and size of the training dataset on translation between Czech and Croatian, German, Hungarian, Slovak, and Spanish.
Negative Lexical Constraints in Neural Machine Translation
This paper explores negative lexical constraining in English to Czech neural machine translation.
Turning Whisper into Real-Time Transcription System
Whisper is one of the recent state-of-the-art multilingual speech recognition and translation models, however, it is not designed for real time transcription.
Assessing Word Importance Using Models Trained for Semantic Tasks
Many NLP tasks require to automatically identify the most significant words in a text.
Breeding Machine Translations: Evolutionary approach to survive and thrive in the world of automated evaluation
With a combination of multiple MT metrics as the fitness function, the proposed method leads to an increase in translation quality as measured by other held-out automatic metrics.
HaVQA: A Dataset for Visual Question Answering and Multimodal Research in Hausa Language
This paper presents HaVQA, the first multimodal dataset for visual question-answering (VQA) tasks in the Hausa language.
Robustness of Multi-Source MT to Transcription Errors
Automatic speech translation is sensitive to speech recognition errors, but in a multilingual scenario, the same content may be available in various languages via simultaneous interpreting, dubbing or subtitling.
Multimodal Shannon Game with Images
To investigate the impact of multimodal information in this game, we use human participants and a language model (LM, GPT-2).
CUNI Submission in WMT22 General Task
We evaluate performance of MBR decoding compared to traditional mixed backtranslation training and we show a possible synergy when using both of the techniques simultaneously.
MT Metrics Correlate with Human Ratings of Simultaneous Speech Translation
There have been several meta-evaluation studies on the correlation between human ratings and offline machine translation (MT) evaluation metrics such as BLEU, chrF2, BertScore and COMET.
Simultaneous Translation for Unsegmented Input: A Sliding Window Approach
In the cascaded approach to spoken language translation (SLT), the ASR output is typically punctuated and segmented into sentences before being passed to MT, since the latter is typically trained on written text.
Sentence Ambiguity, Grammaticality and Complexity Probes
It is unclear whether, how and where large pre-trained language models capture subtle linguistic traits like ambiguity, grammaticality and sentence complexity.
ALIGNMEET: A Comprehensive Tool for Meeting Annotation, Alignment, and Evaluation
To facilitate the research in this area, we present ALIGNMEET, a comprehensive tool for meeting annotation, alignment, and evaluation.
Hausa Visual Genome: A Dataset for Multi-Modal English to Hausa Machine Translation
The Hausa Visual Genome is the first dataset of its kind and can be used for Hausa-English machine translation, multi-modal research, and image description, among various other natural language processing and generation tasks.
CUNI-KIT System for Simultaneous Speech Translation Task at IWSLT 2022
In this paper, we describe our submission to the Simultaneous Speech Translation at IWSLT 2022.
EMMT: A simultaneous eye-tracking, 4-electrode EEG and audio corpus for multi-modal reading and translation scenarios
We present the Eyetracked Multi-Modal Translation (EMMT) corpus, a dataset containing monocular eye movement recordings, audio and 4-electrode electroencephalogram (EEG) data of 43 participants.
Short-Term Word-Learning in a Dynamically Changing Environment
In this paper we study, a) methods to acquire important words for this memory dynamically and, b) the trade-off between improvement in recognition accuracy of new words and the potential danger of false alarms for those added words.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Continuous Rating as Reliable Human Evaluation of Simultaneous Speech Translation
Simultaneous speech translation (SST) can be evaluated on simulated online events where human evaluators watch subtitled videos and continuously express their satisfaction by pressing buttons (so called Continuous Rating).
The Reality of Multi-Lingual Machine Translation
Machine translation is for us a prime example of deep learning applications where human skills and learning capabilities are taken as a benchmark that many try to match and surpass.
CUNI systems for WMT21: Terminology translation Shared Task
Our approach is based on providing the desired translations alongside the input sentence and training the model to use these provided terms.
CUNI systems for WMT21: Multilingual Low-Resource Translation for Indo-European Languages Shared Task
This paper describes Charles University submission for Multilingual Low-Resource Translation for Indo-European Languages shared task at WMT21.
Sequence Length is a Domain: Length-based Overfitting in Transformer Models
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.
Neural Machine Translation Quality and Post-Editing Performance
We test the natural expectation that using MT in professional translation saves human processing time.
Coarse-To-Fine And Cross-Lingual ASR Transfer
End-to-end neural automatic speech recognition systems achieved recently state-of-the-art results, but they require large datasets and extensive computing resources.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
End-to-End Lexically Constrained Machine Translation for Morphologically Rich Languages
Lexically constrained machine translation allows the user to manipulate the output sentence by enforcing the presence or absence of certain words and phrases.
Lost in Interpreting: Speech Translation from Source or Interpreter?
Interpreters facilitate multi-lingual meetings but the affordable set of languages is often smaller than what is needed.
Unsupervised Multilingual Sentence Embeddings for Parallel Corpus Mining
Existing models of multilingual sentence embeddings require large parallel data resources which are not available for low-resource languages.
Backtranslation Feedback Improves User Confidence in MT, Not Quality
Translating text into a language unknown to the text's author, dubbed outbound translation, is a modern need for which the user experience has significant room for improvement, beyond the basic machine translation facility.
THEaiTRE 1.0: Interactive generation of theatre play scripts
We present the first version of a system for interactive generation of theatre play scripts.
Findings of the 2020 Conference on Machine Translation (WMT20)
In the news task, participants were asked to build machine translation systems for any of 11 language pairs, to be evaluated on test sets consisting mainly of news stories.
How Many Pages? Paper Length Prediction from the Metadata
Being able to predict the length of a scientific paper may be helpful in numerous situations.
CUNI Systems for the Unsupervised and Very Low Resource Translation Task in WMT20
This paper presents a description of CUNI systems submitted to the WMT20 task on unsupervised and very low-resource supervised machine translation between German and Upper Sorbian.
Unsupervised Pretraining for Neural Machine Translation Using Elastic Weight Consolidation
In our method, we initialize the weights of the encoder and decoder with two language models that are trained with monolingual data and then fine-tune the model on parallel data using Elastic Weight Consolidation (EWC) to avoid forgetting of the original language modeling tasks.
Presenting Simultaneous Translation in Limited Space
Furthermore, we propose a way how to estimate the overall usability of the combination of automatic translation and subtitling by measuring the quality, latency, and stability on a test set, and propose an improved measure for translation latency.
THEaiTRE: Artificial Intelligence to Write a Theatre Play
We present THEaiTRE, a starting project aimed at automatic generation of theatre play scripts.
Automating Text Naturalness Evaluation of NLG Systems
Instead of relying on human participants for scoring or labeling the text samples, we propose to automate the process by using a human likeliness metric we define and a discrimination procedure based on large pretrained language models with their probability distributions.
ELITR Non-Native Speech Translation at IWSLT 2020
This paper is an ELITR system submission for the non-native speech translation task at IWSLT 2020.
Human or Machine: Automating Human Likeliness Evaluation of NLG Texts
Automatic evaluation of various text quality criteria produced by data-driven intelligent methods is very common and useful because it is cheap, fast, and usually yields repeatable results.
Two Huge Title and Keyword Generation Corpora of Research Articles
Recent developments in sequence-to-sequence learning with neural networks have considerably improved the quality of automatically generated text summaries and document keywords, stipulating the need for even bigger training corpora.
Outbound Translation User Interface Ptakopet: A Pilot Study
It is not uncommon for Internet users to have to produce a text in a foreign language they have very little knowledge of and are unable to verify the translation quality.
Promoting the Knowledge of Source Syntax in Transformer NMT Is Not Needed
The data manipulation techniques, recommended in previous works, prove ineffective in large data settings.
Keyphrase Generation: A Multi-Aspect Survey
In this survey, we examine various aspects of the extractive keyphrase generation methods and focus mostly on the more recent abstractive methods that are based on neural networks.
In Search for Linear Relations in Sentence Embedding Spaces
We present an introductory investigation into continuous-space vector representations of sentences.
Efficiently Reusing Old Models Across Languages via Transfer Learning
To show the applicability of our method, we recycle a Transformer model trained by different researchers and use it to seed models for different language pairs.
Efficiency Metrics for Data-Driven Models: A Text Summarization Case Study
Using data-driven models for solving text summarization or similar tasks has become very common in the last years.
SAO WMT19 Test Suite: Machine Translation of Audit Reports
This paper describes a machine translation test set of documents from the auditing domain and its use as one of the "test suites" in the WMT19 News Translation Task for translation directions involving Czech, English and German.
A Test Suite and Manual Evaluation of Document-Level NMT at WMT19
As the quality of machine translation rises and neural machine translation (NMT) is moving from sentence to document level translations, it is becoming increasingly difficult to evaluate the output of translation systems.
A Speech Test Set of Practice Business Presentations with Additional Relevant Texts
We present a test corpus of audio recordings and transcriptions of presentations of students' enterprises together with their slides and web-pages.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
CUNI Systems for the Unsupervised News Translation Task in WMT 2019
In this paper we describe the CUNI translation system used for the unsupervised news shared task of the ACL 2019 Fourth Conference on Machine Translation (WMT19).
Hindi Visual Genome: A Dataset for Multimodal English-to-Hindi Machine Translation
We present ``Hindi Visual Genome'', a multimodal dataset consisting of text and images suitable for English-Hindi multimodal machine translation task and multimodal research.
Keyphrase Generation: A Text Summarization Struggle
Most of the proposed supervised and unsupervised methods for keyphrase generation are unable to produce terms that are valuable but do not appear in the text.
Sentiment Analysis of Czech Texts: An Algorithmic Survey
In the area of online communication, commerce and transactions, analyzing sentiment polarity of texts written in various natural languages has become crucial.
Trivial Transfer Learning for Low-Resource Neural Machine Translation
We present a simple transfer learning method, where we first train a "parent" model for a high-resource language pair and then continue the training on a lowresource pair only by replacing the training corpus.
Low Resource Neural Machine Translation
Low-Resource Neural Machine Translation
+2
SubGram: Extending Skip-gram Word Representation with Substrings
Skip-gram (word2vec) is a recent method for creating vector representations of words ("distributed word representations") using a neural network.
Morphological and Language-Agnostic Word Segmentation for NMT
The state of the art of handling rich morphology in neural machine translation (NMT) is to break word forms into subword units, so that the overall vocabulary size of these units fits the practical limits given by the NMT model and GPU memory capacity.
Are BLEU and Meaning Representation in Opposition?
One of possible ways of obtaining continuous-space sentence representations is by training neural machine translation (NMT) systems.
Extracting Parallel Paragraphs from Common Crawl
Most of the current methods for mining parallel texts from the web assume that web pages of web sites share same structure across languages.
Training Tips for the Transformer Model
This article describes our experiments in neural machine translation using the recent Tensor2Tensor framework and the Transformer sequence-to-sequence model (Vaswani et al., 2017).
An Exploration of Word Embedding Initialization in Deep-Learning Tasks
We support this hypothesis by observing the performance in learning lexical relations and by the fact that the network can learn to perform reasonably in its task even with fixed random embeddings.
Paying Attention to Multi-Word Expressions in Neural Machine Translation
Processing of multi-word expressions (MWEs) is a known problem for any natural language processing task.
LanideNN: Multilingual Language Identification on Character Window
In language identification, a common first step in natural language processing, we want to automatically determine the language of some input text.
Target-Side Context for Discriminative Models in Statistical Machine Translation
Discriminative translation models utilizing source context have been shown to help statistical machine translation performance.
CUNI System for WMT16 Automatic Post-Editing and Multimodal Translation Tasks
Neural sequence to sequence learning recently became a very promising paradigm in machine translation, achieving competitive results with statistical phrase-based systems.
