Search Results for author:
Found 29 papers, 11 papers with code
Speed-optimized, Compact Student Models that Distill Knowledge from a Larger Teacher Model: the UEDIN-CUNI Submission to the WMT 2020 News Translation Task
We describe the joint submission of the University of Edinburgh and Charles University, Prague, to the Czech/English track in the WMT 2020 Shared Task on News Translation.
The University of Edinburgh’s English-German and English-Hausa Submissions to the WMT21 News Translation Task
This paper presents the University of Edinburgh’s constrained submissions of English-German and English-Hausa systems to the WMT 2021 shared task on news translation.
Efficient Machine Translation with Model Pruning and Quantization
We participated in all tracks of the WMT 2021 efficient machine translation task: single-core CPU, multi-core CPU, and GPU hardware with throughput and latency conditions.
OpusCleaner and OpusTrainer, open source toolkits for training Machine Translation and Large language models
Developing high quality machine translation systems is a labour intensive, challenging and confusing process for newcomers to the field.
The Ups and Downs of Large Language Model Inference with Vocabulary Trimming by Language Heuristics
Deploying large language models (LLMs) encounters challenges due to intensive computational and memory requirements.
Terminology-Aware Translation with Constrained Decoding and Large Language Model Prompting
Terminology correctness is important in the downstream application of machine translation, and a prevalent way to ensure this is to inject terminology constraints into a translation system.
Monolingual or Multilingual Instruction Tuning: Which Makes a Better Alpaca
Foundational large language models (LLMs) can be instruction-tuned to perform open-domain question answering, facilitating applications like chat assistants.
An Open Dataset and Model for Language Identification
We achieve this by training on a curated dataset of monolingual data, the reliability of which we ensure by auditing a sample from each source and each language manually.
The Edinburgh International Accents of English Corpus: Towards the Democratization of English ASR
Although the great many advances in English automatic speech recognition (ASR) over the past decades, results are usually reported based on test datasets which fail to represent the diversity of English as spoken today around the globe.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Low-Rank Softmax Can Have Unargmaxable Classes in Theory but Rarely in Practice
Classifiers in natural language processing (NLP) often have a large number of output classes.
TranslateLocally: Blazing-fast translation running on the local CPU
Every day, millions of people sacrifice their privacy and browsing habits in exchange for online machine translation.
The Highs and Lows of Simple Lexical Domain Adaptation Approaches for Neural Machine Translation
Machine translation systems are vulnerable to domain mismatch, especially in a low-resource scenario.
Not all parameters are born equal: Attention is mostly what you need
We show that the decision about whether a component is frozen or allowed to train is at least as important for the final model performance as its number of parameters.
Character Mapping and Ad-hoc Adaptation: Edinburgh's IWSLT 2020 Open Domain Translation System
This paper describes the University of Edinburgh{'}s neural machine translation systems submitted to the IWSLT 2020 open domain Japanese$\leftrightarrow$Chinese translation task.
Edinburgh's Submissions to the 2020 Machine Translation Efficiency Task
We participated in all tracks of the Workshop on Neural Generation and Translation 2020 Efficiency Shared Task: single-core CPU, multi-core CPU, and GPU.
Parallel Sentence Mining by Constrained Decoding
We present a novel method to extract parallel sentences from two monolingual corpora, using neural machine translation.
In Neural Machine Translation, What Does Transfer Learning Transfer?
Transfer learning improves quality for low-resource machine translation, but it is unclear what exactly it transfers.
Domain, Translationese and Noise in Synthetic Data for Neural Machine Translation
The quality of neural machine translation can be improved by leveraging additional monolingual resources to create synthetic training data.
Combining Global Sparse Gradients with Local Gradients in Distributed Neural Network Training
One way to reduce network traffic in multi-node data-parallel stochastic gradient descent is to only exchange the largest gradients.
From Research to Production and Back: Ludicrously Fast Neural Machine Translation
Taking our dominating submissions to the previous edition of the shared task as a starting point, we develop improved teacher-student training via multi-agent dual-learning and noisy backward-forward translation for Transformer-based student models.
The University of Edinburgh's Submissions to the WMT19 News Translation Task
For all translation directions, we created or used back-translations of monolingual data in the target language as additional synthetic training data.
Similar Minds Post Alike: Assessment of Suicide Risk Using a Hybrid Model
We approached the problem with three separate models: a behaviour model; a language model and a hybrid model.
The University of Edinburgh's Submissions to the WMT18 News Translation Task
The University of Edinburgh made submissions to all 14 language pairs in the news translation task, with strong performances in most pairs.
Accelerating Asynchronous Stochastic Gradient Descent for Neural Machine Translation
In order to extract the best possible performance from asynchronous stochastic gradient descent one must increase the mini-batch size and scale the learning rate accordingly.
Marian: Fast Neural Machine Translation in C++
We present Marian, an efficient and self-contained Neural Machine Translation framework with an integrated automatic differentiation engine based on dynamic computation graphs.
Fast, Scalable Phrase-Based SMT Decoding
The utilization of statistical machine translation (SMT) has grown enormously over the last decade, many using open-source software developed by the NLP community.
