Search Results for author:
Found 97 papers, 14 papers with code
The IWSLT 2011 Evaluation Campaign on Automatic Talk Translation
We report here on the eighth evaluation campaign organized in 2011 by the IWSLT workshop series.
Manual Analysis of Structurally Informed Reordering in German-English Machine Translation
However, it is a crucial aspect for humans when deciding on translation quality.
Lexical Translation Model Using a Deep Neural Network Architecture
In this paper we combine the advantages of a model using global source sentence contexts, the Discriminative Word Lexicon, and neural networks.
Pre-Translation for Neural Machine Translation
We analyzed the influence of the quality of the initial system on the final result.
Toward Multilingual Neural Machine Translation with Universal Encoder and Decoder
In this paper, we present our first attempts in building a multilingual Neural Machine Translation framework under a unified approach.
Lightly Supervised Quality Estimation
Evaluating the quality of output from language processing systems such as machine translation or speech recognition is an essential step in ensuring that they are sufficient for practical use.
Neural Lattice-to-Sequence Models for Uncertain Inputs
In this work, we extend the TreeLSTM (Tai et al., 2015) into a LatticeLSTM that is able to consume word lattices, and can be used as encoder in an attentional encoder-decoder model.
Analyzing Neural MT Search and Model Performance
By separating the search space and the modeling using $n$-best list reranking, we analyze the influence of both parts of an NMT system independently.
Exploiting Linguistic Resources for Neural Machine Translation Using Multi-task Learning
Linguistic resources such as part-of-speech (POS) tags have been extensively used in statistical machine translation (SMT) frameworks and have yielded better performances.
Comparison of Decoding Strategies for CTC Acoustic Models
The CTC loss function maps an input sequence of observable feature vectors to an output sequence of symbols.
Transcribing Against Time
We investigate the problem of manually correcting errors from an automatic speech transcript in a cost-sensitive fashion.
Effective Strategies in Zero-Shot Neural Machine Translation
In this paper, we proposed two strategies which can be applied to a multilingual neural machine translation system in order to better tackle zero-shot scenarios despite not having any parallel corpus.
An End-to-End Goal-Oriented Dialog System with a Generative Natural Language Response Generation
Furthermore, by using a feedforward neural network, we are able to generate the output word by word and are no longer restricted to a fixed number of possible response candidates.
Automated Evaluation of Out-of-Context Errors
We present a new approach to evaluate computational models for the task of text understanding by the means of out-of-context error detection.
Self-Attentional Acoustic Models
Self-attention is a method of encoding sequences of vectors by relating these vectors to each-other based on pairwise similarities.
Robust and Scalable Differentiable Neural Computer for Question Answering
Deep learning models are often not easily adaptable to new tasks and require task-specific adjustments.
A Hierarchical Approach to Neural Context-Aware Modeling
Our approach overcomes recent limitations with extended narratives through a multi-layered computational approach to generate an abstract context representation.
Low-Latency Neural Speech Translation
After adaptation, we are able to reduce the number of corrections displayed during incremental output construction by 45%, without a decrease in translation quality.
KIT Lecture Translator: Multilingual Speech Translation with One-Shot Learning
{\%} Combining these techniques, we are able to provide an adapted speech translation system for several European languages.
Towards one-shot learning for rare-word translation with external experts
Neural machine translation (NMT) has significantly improved the quality of automatic translation models.
The Karlsruhe Institute of Technology Systems for the News Translation Task in WMT 2018
We present our experiments in the scope of the news translation task in WMT 2018, in directions: English→German.
Optimizing Segmentation Granularity for Neural Machine Translation
However, the granularity of these subword units is a hyperparameter to be tuned for each language and task, using methods such as grid search.
Towards Fluent Translations from Disfluent Speech
We introduce a corpus of cleaned target data for the Fisher Spanish-English dataset for this task.
Multi-task learning to improve natural language understanding
When building a neural network-based Natural Language Understanding component, one main challenge is to collect enough training data.
Attention-Passing Models for Robust and Data-Efficient End-to-End Speech Translation
Speech translation has traditionally been approached through cascaded models consisting of a speech recognizer trained on a corpus of transcribed speech, and a machine translation system trained on parallel texts.
Very Deep Self-Attention Networks for End-to-End Speech Recognition
Recently, end-to-end sequence-to-sequence models for speech recognition have gained significant interest in the research community.
Improving Zero-shot Translation with Language-Independent Constraints
We investigated the behaviour of such models on the standard IWSLT 2017 multilingual dataset.
Incremental processing of noisy user utterances in the spoken language understanding task
The state-of-the-art neural network architectures make it possible to create spoken language understanding systems with high quality and fast processing time.
Natural Language Understanding
Spoken Language Understanding
Modeling Confidence in Sequence-to-Sequence Models
We show improvements on segment-level confidence estimation as well as on confidence estimation for source tokens.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Improving sequence-to-sequence speech recognition training with on-the-fly data augmentation
Sequence-to-Sequence (S2S) models recently started to show state-of-the-art performance for automatic speech recognition (ASR).
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Low Latency ASR for Simultaneous Speech Translation
User studies have shown that reducing the latency of our simultaneous lecture translation system should be the most important goal.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Machine Translation with Unsupervised Length-Constraints
In this paper, we explore one of these, the generation of constraint translation.
Low-Latency Sequence-to-Sequence Speech Recognition and Translation by Partial Hypothesis Selection
On How2 English-Portuguese speech translation, we reduce latency to 0. 7 second (-84% rel.)
Sequence-To-Sequence Speech Recognition
speech-recognition
+1
Adapting End-to-End Speech Recognition for Readable Subtitles
The experiments show that with limited data far less than needed for training a model from scratch, we can adapt a Transformer-based ASR model to incorporate both transcription and compression capabilities.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
FINDINGS OF THE IWSLT 2020 EVALUATION CAMPAIGN
The evaluation campaign of the International Conference on Spoken Language Translation (IWSLT 2020) featured this year six challenge tracks: (i) Simultaneous speech translation, (ii) Video speech translation, (iii) Offline speech translation, (iv) Conversational speech translation, (v) Open domain translation, and (vi) Non-native speech translation.
Improving Zero-Shot Translation by Disentangling Positional Information
The difficulty of generalizing to new translation directions suggests the model representations are highly specific to those language pairs seen in training.
Continuous Learning in Neural Machine Translation using Bilingual Dictionaries
For humans, as well as for machine translation, bilingual dictionaries are a promising knowledge source to continuously integrate new knowledge.
Unsupervised Machine Translation On Dravidian Languages
We show that unifying the writing systems is essential in unsupervised translation between the Dravidian languages.
Tutorial Proposal: End-to-End Speech Translation
Speech translation is the translation of speech in one language typically to text in another, traditionally accomplished through a combination of automatic speech recognition and machine translation.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Cost-Effective Training in Low-Resource Neural Machine Translation
Although AL is shown to be helpful with large budgets, it is not enough to build high-quality translation systems in these low-resource conditions.
Tackling data scarcity in speech translation using zero-shot multilingual machine translation techniques
We investigate whether these ideas can be applied to speech translation, by building ST models trained on speech transcription and text translation data.
Multilingual Simultaneous Speech Translation
Based on a technique to adapt end-to-end monolingual models, we investigate multilingual models and different architectures (end-to-end and cascade) on the ability to perform online speech translation.
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.
LibriS2S: A German-English Speech-to-Speech Translation Corpus
In contrast, the activities in the area of speech-to-speech translation is still limited, although it is essential to overcome the language barrier.
Adaptive multilingual speech recognition with pretrained models
Multilingual speech recognition with supervised learning has achieved great results as reflected in recent research.
Learning an Artificial Language for Knowledge-Sharing in Multilingual Translation
In this work, we discretize the encoder output latent space of multilingual models by assigning encoder states to entries in a codebook, which in effect represents source sentences in a new artificial language.
Efficient Speech Translation with Pre-trained Models
When building state-of-the-art speech translation models, the need for large computational resources is a significant obstacle due to the large training data size and complex models.
Towards continually learning new languages
Multilingual speech recognition with neural networks is often implemented with batch-learning, when all of the languages are available before training.
Train Global, Tailor Local: Minimalist Multilingual Translation into Endangered Languages
We examine two approaches: 1. best selection of seed sentences to jump start translations in a new language in view of best generalization to the remainder of a larger targeted text(s), and 2. we adapt large general multilingual translation engines from many other languages to focus on a specific text in a new, unknown language.
Perturbation-based QE: An Explainable, Unsupervised Word-level Quality Estimation Method for Blackbox Machine Translation
Quality Estimation (QE) is the task of predicting the quality of Machine Translation (MT) system output, without using any gold-standard translation references.
Gender Lost In Translation: How Bridging The Gap Between Languages Affects Gender Bias in Zero-Shot Multilingual Translation
Neural machine translation (NMT) models often suffer from gender biases that harm users and society at large.
KIT's Multilingual Speech Translation System for IWSLT 2023
In this paper, we describe our speech translation system for the multilingual track of IWSLT 2023, which evaluates translation quality on scientific conference talks.
End-to-End Evaluation for Low-Latency Simultaneous Speech Translation
Secondly, we compare different approaches to low-latency speech translation using this framework.
How Transferable are Attribute Controllers on Pretrained Multilingual Translation Models?
This gap is out of sync with recent progress in pretrained massively multilingual translation models.
Audience-specific Explanations for Machine Translation
In this work, we propose a semi-automatic technique to extract these explanations from a large parallel corpus.
Contextual Refinement of Translations: Large Language Models for Sentence and Document-Level Post-Editing
Building on the LLM's exceptional ability to process and generate lengthy sequences, we also propose extending our approach to document-level translation.
Language-Independent Representations Improve Zero-Shot Summarization
In this work, we focus on summarization and tackle the problem through the lens of language-independent representations.
Effective combination of pretrained models - KIT@IWSLT2022
Pretrained models in acoustic and textual modalities can potentially improve speech translation for both Cascade and End-to-end approaches.
Maastricht University’s Large-Scale Multilingual Machine Translation System for WMT 2021
We present our development of the multilingual machine translation system for the large-scale multilingual machine translation task at WMT 2021.
KIT’s IWSLT 2018 SLT Translation System
The baseline system is a cascade of an ASR system, a system to segment the ASR output and a neural machine translation system.
Integrating Encyclopedic Knowledge into Neural Language Models
Neural models have recently shown big improvements in the performance of phrase-based machine translation.
The IWSLT 2016 Evaluation Campaign
The IWSLT 2016 Evaluation Campaign featured two tasks: the translation of talks and the translation of video conference conversations.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Multilingual Disfluency Removal using NMT
In this paper, we investigate a multilingual approach for speech disfluency removal.
Adaptation and Combination of NMT Systems: The KIT Translation Systems for IWSLT 2016
In addition, we investigated methods to combine NMT systems that encode the input as well as the output differently.
The IWSLT 2019 KIT Speech Translation System
This paper describes KIT’s submission to the IWSLT 2019 Speech Translation task on two sub-tasks corresponding to two different datasets.
The IWSLT 2019 Evaluation Campaign
The IWSLT 2019 evaluation campaign featured three tasks: speech translation of (i) TED talks and (ii) How2 instructional videos from English into German and Portuguese, and (iii) text translation of TED talks from English into Czech.
Maastricht University’s Multilingual Speech Translation System for IWSLT 2021
The task in this track is to build multilingual speech translation systems in supervised and zero-shot directions.
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.
The IWSLT 2018 Evaluation Campaign
The International Workshop of Spoken Language Translation (IWSLT) 2018 Evaluation Campaign featured two tasks: low-resource machine translation and speech translation.
Toward Robust Neural Machine Translation for Noisy Input Sequences
We note that unlike our baseline model, models trained on noisy data are able to generate outputs of proper length even for noisy inputs, while gradually reducing output length for higher amount of noise, as might also be expected from a human translator.
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.
Domain-independent Punctuation and Segmentation Insertion
Experiments show that generalizing rare and unknown words greatly improves the punctuation insertion performance, reaching up to 8. 8 points of improvement in F-score when applied to the out-of-domain test scenario.
KIT’s Multilingual Neural Machine Translation systems for IWSLT 2017
For the SLT track, in addition to a monolingual neural translation system used to generate correct punctuations and true cases of the data prior to training our multilingual system, we introduced a noise model in order to make our system more robust.
Overview of the IWSLT 2017 Evaluation Campaign
The IWSLT 2017 evaluation campaign has organised three tasks.
