Search Results for author:
Found 24 papers, 9 papers with code
GFST: Gender-Filtered Self-Training for More Accurate Gender in Translation
Targeted evaluations have found that machine translation systems often output incorrect gender in translations, even when the gender is clear from context.
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.
Distilling Multiple Domains for Neural Machine Translation
Neural machine translation achieves impressive results in high-resource conditions, but performance often suffers when the input domain is low-resource.
PEAVS: Perceptual Evaluation of Audio-Visual Synchrony Grounded in Viewers' Opinion Scores
Recent advancements in audio-visual generative modeling have been propelled by progress in deep learning and the availability of data-rich benchmarks.
End-to-End Single-Channel Speaker-Turn Aware Conversational Speech Translation
Conventional speech-to-text translation (ST) systems are trained on single-speaker utterances, and they may not generalize to real-life scenarios where the audio contains conversations by multiple speakers.
Improving Isochronous Machine Translation with Target Factors and Auxiliary Counters
To translate speech for automatic dubbing, machine translation needs to be isochronous, i. e. translated speech needs to be aligned with the source in terms of speech durations.
Jointly Optimizing Translations and Speech Timing to Improve Isochrony in Automatic Dubbing
Automatic dubbing (AD) is the task of translating the original speech in a video into target language speech.
Improving Robustness of Retrieval Augmented Translation via Shuffling of Suggestions
Several recent studies have reported dramatic performance improvements in neural machine translation (NMT) by augmenting translation at inference time with fuzzy-matches retrieved from a translation memory (TM).
Improving Retrieval Augmented Neural Machine Translation by Controlling Source and Fuzzy-Match Interactions
We explore zero-shot adaptation, where a general-domain model has access to customer or domain specific parallel data at inference time, but not during training.
Automatic Evaluation and Analysis of Idioms in Neural Machine Translation
A major open problem in neural machine translation (NMT) is the translation of idiomatic expressions, such as "under the weather".
Embarrassingly Easy Document-Level MT Metrics: How to Convert Any Pretrained Metric Into a Document-Level Metric
Our experimental results support our initial hypothesis and show that a simple extension of the metrics permits them to take advantage of context to resolve ambiguities in the reference.
Sockeye 3: Fast Neural Machine Translation with PyTorch
When running comparable models, Sockeye 3 is up to 126% faster than other PyTorch implementations on GPUs and up to 292% faster on CPUs.
Isometric MT: Neural Machine Translation for Automatic Dubbing
Automatic dubbing (AD) is among the machine translation (MT) use cases where translations should match a given length to allow for synchronicity between source and target speech.
Isochrony-Aware Neural Machine Translation for Automatic Dubbing
We introduce the task of isochrony-aware machine translation which aims at generating translations suitable for dubbing.
Faithful Target Attribute Prediction in Neural Machine Translation
The training data used in NMT is rarely controlled with respect to specific attributes, such as word casing or gender, which can cause errors in translations.
Improving Gender Translation Accuracy with Filtered Self-Training
Targeted evaluations have found that machine translation systems often output incorrect gender, even when the gender is clear from context.
Evaluating Robustness to Input Perturbations for Neural Machine Translation
Neural Machine Translation (NMT) models are sensitive to small perturbations in the input.
Joint translation and unit conversion for end-to-end localization
A variety of natural language tasks require processing of textual data which contains a mix of natural language and formal languages such as mathematical expressions.
Training Neural Machine Translation To Apply Terminology Constraints
This paper proposes a novel method to inject custom terminology into neural machine translation at run time.
Generating E-Commerce Product Titles and Predicting their Quality
The setting requires the generation process to be fast and the generated title to be both human-readable and concise.
Multi-lingual neural title generation for e-Commerce browse pages
These browse pages require a title describing the content of the page.
Generating titles for millions of browse pages on an e-Commerce site
We present two approaches to generate titles for browse pages in five different languages, namely English, German, French, Italian and Spanish.
