Search Results for author:
Found 60 papers, 16 papers with code
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.
Findings of the WMT 2021 Shared Task on Efficient Translation
The machine translation efficiency task challenges participants to make their systems faster and smaller with minimal impact on translation quality.
Losing Heads in the Lottery: Pruning Transformer Attention in Neural Machine Translation
The attention mechanism is the crucial component of the transformer architecture.
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.
Constrained Regeneration for Cross-Lingual Query-Focused Extractive Summarization
Query-focused summaries of foreign-language, retrieved documents can help a user understand whether a document is actually relevant to the query term.
Pruning Neural Machine Translation for Speed Using Group Lasso
In the WMT 2021 Efficiency Task, our pruned and quantised models are 1. 9–2. 7x faster at the cost 0. 9–1. 7 BLEU in comparison to the unoptimised baselines.
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.
Cheat Codes to Quantify Missing Source Information in Neural Machine Translation
This paper describes a method to quantify the amount of information H(t|s) added by the target sentence t that is not present in the source s in a neural machine translation system.
The EuroPat Corpus: A Parallel Corpus of European Patent Data
We present the EuroPat corpus of patent-specific parallel data for 6 official European languages paired with English: German, Spanish, French, Croatian, Norwegian, and Polish.
The Llama 3 Herd of Models
This paper presents a new set of foundation models, called Llama 3.
Ranked #3 on
Multi-task Language Understanding
on MMLU
Code-Switched Language Identification is Harder Than You Think
Code switching (CS) is a very common phenomenon in written and spoken communication but one that is handled poorly by many natural language processing applications.
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.
Iterative Translation Refinement with Large Language Models
We propose iteratively prompting a large language model to self-correct a translation, with inspiration from their strong language understanding and translation capability as well as a human-like translation approach.
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.
Efficient Methods for Natural Language Processing: A Survey
Recent work in natural language processing (NLP) has yielded appealing results from scaling model parameters and training data; however, using only scale to improve performance means that resource consumption also grows.
No Language Left Behind: Scaling Human-Centered Machine Translation
Driven by the goal of eradicating language barriers on a global scale, machine translation has solidified itself as a key focus of artificial intelligence research today.
Ranked #1 on
Machine Translation
on IWSLT2017 French-English
(SacreBLEU metric)
Exploring Diversity in Back Translation for Low-Resource Machine Translation
We also find evidence that lexical diversity is more important than syntactic for back translation performance.
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.
Gender Bias Amplification During Speed-Quality Optimization in Neural Machine Translation
Is bias amplified when neural machine translation (NMT) models are optimized for speed and evaluated on generic test sets using BLEU?
Fully Synthetic Data Improves Neural Machine Translation with Knowledge Distillation
This paper explores augmenting monolingual data for knowledge distillation in neural machine translation.
Approaching Neural Chinese Word Segmentation as a Low-Resource Machine Translation Task
Chinese word segmentation has entered the deep learning era which greatly reduces the hassle of feature engineering.
Chinese Word Segmentation
Low Resource Neural Machine Translation
+3
The Sockeye 2 Neural Machine Translation Toolkit at AMTA 2020
We present Sockeye 2, a modernized and streamlined version of the Sockeye neural machine translation (NMT) toolkit.
Compressing Neural Machine Translation Models with 4-bit Precision
We empirically show that NMT models based on Transformer or RNN architecture can be compressed up to 4-bit precision without any noticeable quality degradation.
Parallel Sentence Mining by Constrained Decoding
We present a novel method to extract parallel sentences from two monolingual corpora, using neural machine translation.
ParaCrawl: Web-Scale Acquisition of Parallel Corpora
We report on methods to create the largest publicly available parallel corpora by crawling the web, using open source software.
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.
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.
Findings of the Fourth Workshop on Neural Generation and Translation
We describe the finding of the Fourth Workshop on Neural Generation and Translation, held in concert with the annual conference of the Association for Computational Linguistics (ACL 2020).
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.
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.
Zero-Resource Neural Machine Translation with Monolingual Pivot Data
An extension to zero-shot NMT is zero-resource NMT, which generates pseudo-parallel corpora using a zero-shot system and further trains the zero-shot system on that data.
Neural Machine Translation with 4-Bit Precision and Beyond
We empirically show that NMT models based on Transformer or RNN architecture can be compressed up to 4-bit precision without any noticeable quality degradation.
Incorporating Source Syntax into Transformer-Based Neural Machine Translation
Transformer-based neural machine translation (NMT) has recently achieved state-of-the-art performance on many machine translation tasks.
Neural Grammatical Error Correction Systems with Unsupervised Pre-training on Synthetic Data
Considerable effort has been made to address the data sparsity problem in neural grammatical error correction.
Ranked #15 on
Grammatical Error Correction
on BEA-2019 (test)
Making Asynchronous Stochastic Gradient Descent Work for Transformers
Asynchronous stochastic gradient descent (SGD) is attractive from a speed perspective because workers do not wait for synchronization.
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.
Findings of the WMT 2018 Shared Task on Parallel Corpus Filtering
We posed the shared task of assigning sentence-level quality scores for a very noisy corpus of sentence pairs crawled from the web, with the goal of sub-selecting 1{\%} and 10{\%} of high-quality data to be used to train machine translation systems.
Multi-Source Syntactic Neural Machine Translation
We introduce a novel multi-source technique for incorporating source syntax into neural machine translation using linearized parses.
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.
Unsupervised Source Hierarchies for Low-Resource Neural Machine Translation
Incorporating source syntactic information into neural machine translation (NMT) has recently proven successful (Eriguchi et al., 2016; Luong et al., 2016).
Low Resource Neural Machine Translation
Low-Resource Neural Machine Translation
+5
Neural Machine Translation Techniques for Named Entity Transliteration
Transliterating named entities from one language into another can be approached as neural machine translation (NMT) problem, for which we use deep attentional RNN encoder-decoder models.
Marian: Cost-effective High-Quality Neural Machine Translation in C++
This paper describes the submissions of the "Marian" team to the WNMT 2018 shared task.
Fast Neural Machine Translation Implementation
This paper describes the submissions to the efficiency track for GPUs at the Workshop for Neural Machine Translation and Generation by members of the University of Edinburgh, Adam Mickiewicz University, Tilde and University of Alicante.
Exploring Hyper-Parameter Optimization for Neural Machine Translation on GPU Architectures
Neural machine translation (NMT) has been accelerated by deep learning neural networks over statistical-based approaches, due to the plethora and programmability of commodity heterogeneous computing architectures such as FPGAs and GPUs and the massive amount of training corpuses generated from news outlets, government agencies and social media.
Approaching Neural Grammatical Error Correction as a Low-Resource Machine Translation Task
Previously, neural methods in grammatical error correction (GEC) did not reach state-of-the-art results compared to phrase-based statistical machine translation (SMT) baselines.
Ranked #1 on
Grammatical Error Correction
on _Restricted_
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.
The University of Edinburgh's Neural MT Systems for WMT17
This paper describes the University of Edinburgh's submissions to the WMT17 shared news translation and biomedical translation tasks.
Sparse Communication for Distributed Gradient Descent
Most configurations work on MNIST, whereas different configurations reduce convergence rate on the more complex translation task.
N-gram Counts and Language Models from the Common Crawl
We contribute 5-gram counts and language models trained on the Common Crawl corpus, a collection over 9 billion web pages.
