Search Results for author:
Found 65 papers, 29 papers with code
GoURMET – Machine Translation for Low-Resourced Languages
The GoURMET project, funded by the European Commission’s H2020 program (under grant agreement 825299), develops models for machine translation, in particular for low-resourced languages.
Samsung and University of Edinburgh’s System for the IWSLT 2019
This paper describes the joint submission to the IWSLT 2019 English to Czech task by Samsung RD Institute, Poland, and the University of Edinburgh.
The University of Edinburgh’s English-Tamil and English-Inuktitut Submissions to the WMT20 News Translation Task
We describe the University of Edinburgh’s submissions to the WMT20 news translation shared task for the low resource language pair English-Tamil and the mid-resource language pair English-Inuktitut.
Non-Autoregressive Machine Translation: It’s Not as Fast as it Seems
In this paper, we point out flaws in the evaluation methodology present in the literature on NAR models and we provide a fair comparison between a state-of-the-art NAR model and the autoregressive submissions to the shared task.
A Neural Verb Lexicon Model with Source-side Syntactic Context for String-to-Tree Machine Translation
String-to-tree MT systems translate verbs without lexical or syntactic context on the source side and with limited target-side context.
Samsung and University of Edinburgh’s System for the IWSLT 2018 Low Resource MT Task
This paper describes the joint submission to the IWSLT 2018 Low Resource MT task by Samsung R&D Institute, Poland, and the University of Edinburgh.
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.
Surprise Language Challenge: Developing a Neural Machine Translation System between Pashto and English in Two Months
We find that starting from an existing large model pre-trained on 50languages leads to far better BLEU scores than pretraining on one high-resource language pair with a smaller model.
Improving Translation of Out Of Vocabulary Words using Bilingual Lexicon Induction in Low-Resource Machine Translation
Dictionary-based data augmentation techniques have been used in the field of domain adaptation to learn words that do not appear in the parallel training data of a machine translation model.
Horses to Zebras: Ontology-Guided Data Augmentation and Synthesis for ICD-9 Coding
We propose data augmentation and synthesis techniques in order to address these scenarios.
Cultural Adaptation of Menus: A Fine-Grained Approach
Machine Translation of Culture-Specific Items (CSIs) poses significant challenges.
Quality or Quantity? On Data Scale and Diversity in Adapting Large Language Models for Low-Resource Translation
Similarly, diversity during SFT has been shown to promote significant transfer in LLMs across languages and tasks.
Sharing Matters: Analysing Neurons Across Languages and Tasks in LLMs
In our work, we investigate how neuron activation is shared across languages by categorizing neurons into four distinct groups according to their responses across different languages for a particular input: all-shared, partial-shared, specific, and non-activated.
Optimising Calls to Large Language Models with Uncertainty-Based Two-Tier Selection
Either a cascading strategy is used, where a smaller LLM or both are called sequentially, or a routing strategy is used, where only one model is ever called.
The Power of Question Translation Training in Multilingual Reasoning: Broadened Scope and Deepened Insights
In this paper, we explore how broadly this method can be applied by examining its effects in reasoning with executable code and reasoning with common sense.
No Train but Gain: Language Arithmetic for training-free Language Adapters enhancement
Modular deep learning is the state-of-the-art solution for lifting the curse of multilinguality, preventing the impact of negative interference and enabling cross-lingual performance in Multilingual Pre-trained Language Models.
Is Modularity Transferable? A Case Study through the Lens of Knowledge Distillation
Moreover, we propose a method that allows the transfer of modules between incompatible PLMs without any change in the inference complexity.
Compact Speech Translation Models via Discrete Speech Units Pretraining
It also avoids speech discretization in inference and is more robust to the DSU tokenization.
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.
Prosody in Cascade and Direct Speech-to-Text Translation: a case study on Korean Wh-Phrases
While there has been a growing interest in developing direct speech translation systems to avoid propagating errors and losing non-verbal content, prior work in direct S2TT has struggled to conclusively establish the advantages of integrating the acoustic signal directly into the translation process.
Machine Translation Meta Evaluation through Translation Accuracy Challenge Sets
We benchmark metric performance, assess their incremental performance over successive campaigns, and measure their sensitivity to a range of linguistic phenomena.
Can GPT-3.5 Generate and Code Discharge Summaries?
Neural coding models were trained on baseline and augmented data and evaluated on a MIMIC-IV test set.
Question Translation Training for Better Multilingual Reasoning
A typical solution is to translate instruction data into all languages of interest, and then train on the resulting multilingual data, which is called translate-training.
Retrieval-augmented Multilingual Knowledge Editing
Knowledge represented in Large Language Models (LLMs) is quite often incorrect and can also become obsolete over time.
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.
Code-Switching with Word Senses for Pretraining in Neural Machine Translation
Lexical ambiguity is a significant and pervasive challenge in Neural Machine Translation (NMT), with many state-of-the-art (SOTA) NMT systems struggling to handle polysemous words (Campolungo et al., 2022).
Cache & Distil: Optimising API Calls to Large Language Models
To curtail the frequency of these calls, one can employ a smaller language model -- a student -- which is continuously trained on the responses of the LLM.
Assessing the Reliability of Large Language Model Knowledge
Large language models (LLMs) have been treated as knowledge bases due to their strong performance in knowledge probing tasks.
Towards Effective Disambiguation for Machine Translation with Large Language Models
Resolving semantic ambiguity has long been recognised as a central challenge in the field of Machine Translation.
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.
When Does Monolingual Data Help Multilingual Translation: The Role of Domain and Model Scale
Next, we analyze the impact of scale (from 90M to 1. 6B parameters) and find it is important for both methods, particularly DAE.
Hallucinations in Large Multilingual Translation Models
Large-scale multilingual machine translation systems have demonstrated remarkable ability to translate directly between numerous languages, making them increasingly appealing for real-world applications.
Prompting Large Language Model for Machine Translation: A Case Study
Research on prompting has shown excellent performance with little or even no supervised training across many tasks.
Extrinsic Evaluation of Machine Translation Metrics
We calculate the correlation between the metric's ability to predict a good/bad translation with the success/failure on the final task for the Translate-Test setup.
MULTI3NLU++: A Multilingual, Multi-Intent, Multi-Domain Dataset for Natural Language Understanding in Task-Oriented Dialogue
We use MULTI3NLU++ to benchmark state-of-the-art multilingual models for the NLU tasks of intent detection and slot labelling for TOD systems in the multilingual setting.
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.
Quantifying Synthesis and Fusion and their Impact on Machine Translation
In this work, we propose to reduce the rigidity of such claims, by quantifying morphological typology at the word and segment level.
Non-Autoregressive Machine Translation: It's Not as Fast as it Seems
In this paper, we point out flaws in the evaluation methodology present in the literature on NAR models and we provide a fair comparison between a state-of-the-art NAR model and the autoregressive submissions to the shared task.
Distributionally Robust Recurrent Decoders with Random Network Distillation
Neural machine learning models can successfully model language that is similar to their training distribution, but they are highly susceptible to degradation under distribution shift, which occurs in many practical applications when processing out-of-domain (OOD) text.
Cross-lingual Intermediate Fine-tuning improves Dialogue State Tracking
In this work, we enhance the transfer learning process by intermediate fine-tuning of pretrained multilingual models, where the multilingual models are fine-tuned with different but related data and/or tasks.
CoPHE: A Count-Preserving Hierarchical Evaluation Metric in Large-Scale Multi-Label Text Classification
We propose a set of metrics for hierarchical evaluation using the depth-based representation.
Multi Label Text Classification
Multi-Label Text Classification
+1
Survey of Low-Resource Machine Translation
We present a survey covering the state of the art in low-resource machine translation research.
Exploring Unsupervised Pretraining Objectives for Machine Translation
Unsupervised cross-lingual pretraining has achieved strong results in neural machine translation (NMT), by drastically reducing the need for large parallel data.
Few-shot learning through contextual data augmentation
Machine translation (MT) models used in industries with constantly changing topics, such as translation or news agencies, need to adapt to new data to maintain their performance over time.
Language Model Prior for Low-Resource Neural Machine Translation
A common solution is to exploit the knowledge of language models (LM) trained on abundant monolingual data.
Bridging Linguistic Typology and Multilingual Machine Translation with Multi-View Language Representations
Sparse language vectors from linguistic typology databases and learned embeddings from tasks like multilingual machine translation have been investigated in isolation, without analysing how they could benefit from each other's language characterisation.
Towards Making the Most of Context in Neural Machine Translation
Document-level machine translation manages to outperform sentence level models by a small margin, but have failed to be widely adopted.
A Latent Morphology Model for Open-Vocabulary Neural Machine Translation
Translation into morphologically-rich languages challenges neural machine translation (NMT) models with extremely sparse vocabularies where atomic treatment of surface forms is unrealistic.
Findings of the Third Workshop on Neural Generation and Translation
This document describes the findings of the Third Workshop on Neural Generation and Translation, held in concert with the annual conference of the Empirical Methods in Natural Language Processing (EMNLP 2019).
On the Importance of Word Boundaries in Character-level Neural Machine Translation
Neural Machine Translation (NMT) models generally perform translation using a fixed-size lexical vocabulary, which is an important bottleneck on their generalization capability and overall translation quality.
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.
Exploring Gap Filling as a Cheaper Alternative to Reading Comprehension Questionnaires when Evaluating Machine Translation for Gisting
A popular application of machine translation (MT) is gisting: MT is consumed as is to make sense of text in a foreign language.
Findings of the Second Workshop on Neural Machine Translation and Generation
This document describes the findings of the Second Workshop on Neural Machine Translation and Generation, held in concert with the annual conference of the Association for Computational Linguistics (ACL 2018).
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.
Evaluating Discourse Phenomena in Neural Machine Translation
Despite gains using BLEU, multi-encoder models give limited improvement in the handling of discourse phenomena: 50% accuracy on our coreference test set and 53. 5% for coherence/cohesion (compared to a non-contextual baseline of 50%).
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.
Deep Architectures for Neural Machine Translation
It has been shown that increasing model depth improves the quality of neural machine translation.
Nematus: a Toolkit for Neural Machine Translation
We present Nematus, a toolkit for Neural Machine Translation.
Predicting Target Language CCG Supertags Improves Neural Machine Translation
Our results on WMT data show that explicitly modeling target-syntax improves machine translation quality for German->English, a high-resource pair, and for Romanian->English, a low-resource pair and also several syntactic phenomena including prepositional phrase attachment.
HUME: Human UCCA-Based Evaluation of Machine Translation
Human evaluation of machine translation normally uses sentence-level measures such as relative ranking or adequacy scales.
Edinburgh Neural Machine Translation Systems for WMT 16
We participated in the WMT 2016 shared news translation task by building neural translation systems for four language pairs, each trained in both directions: English<->Czech, English<->German, English<->Romanian and English<->Russian.
Ranked #1 on
Machine Translation
on WMT2016 Czech-English
Improving Neural Machine Translation Models with Monolingual Data
Neural Machine Translation (NMT) has obtained state-of-the art performance for several language pairs, while only using parallel data for training.
Neural Machine Translation of Rare Words with Subword Units
Neural machine translation (NMT) models typically operate with a fixed vocabulary, but translation is an open-vocabulary problem.
Ranked #1 on
Machine Translation
on WMT2015 English-Russian
