6 papers · 1 filter
Token-level Ensembling of Models with Different Vocabularies
Rachel Wicks, Kartik Ravisankar, Xinchen Yang +2
Model ensembling is a technique to combine the predicted distributions of two or more models, often leading to improved robustness and performance. For ensembling in text generatio…
CTC-GMM: CTC guided modality matching for fast and accurate streaming speech translation
Rui Zhao, Jinyu Li, Ruchao Fan +1
Models for streaming speech translation (ST) can achieve high accuracy and low latency if they're developed with vast amounts of paired audio in the source language and written tex…
PyMarian: Fast Neural Machine Translation and Evaluation in Python
Thamme Gowda, Roman Grundkiewicz, Elijah Rippeth +2
The deep learning language of choice these days is Python; measured by factors such as available libraries and technical support, it is hard to beat. At the same time, software wri…
Navigating the Metrics Maze: Reconciling Score Magnitudes and Accuracies
Tom Kocmi, Vilém Zouhar, Christian Federmann +1
Ten years ago a single metric, BLEU, governed progress in machine translation research. For better or worse, there is no such consensus today, and consequently it is difficult for…
Recovering document annotations for sentence-level bitext
Rachel Wicks, Matt Post, Philipp Koehn
Data availability limits the scope of any given task. In machine translation, historical models were incapable of handling longer contexts, so the lack of document-level datasets w…
Escaping the sentence-level paradigm in machine translation
Matt Post, Marcin Junczys-Dowmunt
It is well-known that document context is vital for resolving a range of translation ambiguities, and in fact the document setting is the most natural setting for nearly all transl…