Search Results for author:
Found 121 papers, 68 papers with code
Wino-X: Multilingual Winograd Schemas for Commonsense Reasoning and Coreference Resolution
We use this resource to investigate whether neural machine translation (NMT) models can perform CoR that requires commonsense knowledge and whether multilingual language models (MLLMs) are capable of CSR across multiple 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.
Edinburgh’s End-to-End Multilingual Speech Translation System for IWSLT 2021
This paper describes Edinburgh’s submissions to the IWSLT2021 multilingual speech translation (ST) task.
Contrastive Conditioning for Assessing Disambiguation in MT: A Case Study of Distilled Bias
Lexical disambiguation is a major challenge for machine translation systems, especially if some senses of a word are trained less often than others.
Exploring the Importance of Source Text in Automatic Post-Editing for Context-Aware Machine Translation
They also highlight blind spots in automatic methods for targeted evaluation and demonstrate the need for human assessment to evaluate document-level translation quality reliably.
ELITR: European Live Translator
ELITR (European Live Translator) project aims to create a speech translation system for simultaneous subtitling of conferences and online meetings targetting up to 43 languages.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
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.
Evaluating Automatic Metrics with Incremental Machine Translation Systems
We introduce a dataset comprising commercial machine translations, gathered weekly over six years across 12 translation directions.
SignCLIP: Connecting Text and Sign Language by Contrastive Learning
We present SignCLIP, which re-purposes CLIP (Contrastive Language-Image Pretraining) to project spoken language text and sign language videos, two classes of natural languages of distinct modalities, into the same space.
An Analysis of BPE Vocabulary Trimming in Neural Machine Translation
We explore threshold vocabulary trimming in Byte-Pair Encoding subword tokenization, a postprocessing step that replaces rare subwords with their component subwords.
Linear-time Minimum Bayes Risk Decoding with Reference Aggregation
Minimum Bayes Risk (MBR) decoding is a text generation technique that has been shown to improve the quality of machine translations, but is expensive, even if a sampling-based approximation is used.
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.
Modular Adaptation of Multilingual Encoders to Written Swiss German Dialect
Creating neural text encoders for written Swiss German is challenging due to a dearth of training data combined with dialectal variation.
Machine Translation Models are Zero-Shot Detectors of Translation Direction
Detecting the translation direction of parallel text has applications for machine translation training and evaluation, but also has forensic applications such as resolving plagiarism or forgery allegations.
Turning English-centric LLMs Into Polyglots: How Much Multilinguality Is Needed?
In experiments across four LLMs, we find that multilingual instruction tuning with as few as two to three languages is both necessary and sufficient to elicit effective cross-lingual generalisation, with the limiting factor being the degree to which a target language is seen during pretraining.
Trained MT Metrics Learn to Cope with Machine-translated References
Neural metrics trained on human evaluations of MT tend to correlate well with human judgments, but their behavior is not fully understood.
A Benchmark for Evaluating Machine Translation Metrics on Dialects Without Standard Orthography
For sensible progress in natural language processing, it is important that we are aware of the limitations of the evaluation metrics we use.
Investigating Multi-Pivot Ensembling with Massively Multilingual Machine Translation Models
Massively multilingual machine translation models allow for the translation of a large number of languages with a single model, but have limited performance on low- and very-low-resource translation directions.
Mitigating Hallucinations and Off-target Machine Translation with Source-Contrastive and Language-Contrastive Decoding
Experiments on the massively multilingual models M2M-100 (418M) and SMaLL-100 show that these methods suppress hallucinations and off-target translations, reducing the number of translations with segment-level chrF2 below 10 by 67-83% on average, and the number of translations with oscillatory hallucinations by 75-92% on average, across 57 tested translation directions.
Uncertainty in Natural Language Generation: From Theory to Applications
Recent advances of powerful Language Models have allowed Natural Language Generation (NLG) to emerge as an important technology that can not only perform traditional tasks like summarisation or translation, but also serve as a natural language interface to a variety of applications.
Towards Unsupervised Recognition of Token-level Semantic Differences in Related Documents
Automatically highlighting words that cause semantic differences between two documents could be useful for a wide range of applications.
Exploiting Biased Models to De-bias Text: A Gender-Fair Rewriting Model
We hypothesise that creating training data in the reverse direction, i. e. starting from gender-fair text, is easier for morphologically complex languages and show that it matches the performance of state-of-the-art rewriting models for English.
What's the Meaning of Superhuman Performance in Today's NLU?
In the last five years, there has been a significant focus in Natural Language Processing (NLP) on developing larger Pretrained Language Models (PLMs) and introducing benchmarks such as SuperGLUE and SQuAD to measure their abilities in language understanding, reasoning, and reading comprehension.
SLTUNET: A Simple Unified Model for Sign Language Translation
We propose SLTUNET, a simple unified neural model designed to support multiple SLTrelated tasks jointly, such as sign-to-gloss, gloss-to-text and sign-to-text translation.
SwissBERT: The Multilingual Language Model for Switzerland
We present SwissBERT, a masked language model created specifically for processing Switzerland-related text.
Efficient CTC Regularization via Coarse Labels for End-to-End Speech Translation
For end-to-end speech translation, regularizing the encoder with the Connectionist Temporal Classification (CTC) objective using the source transcript or target translation as labels can greatly improve quality metrics.
Improving the Cross-Lingual Generalisation in Visual Question Answering
While several benefits were realized for multilingual vision-language pretrained models, recent benchmarks across various tasks and languages showed poor cross-lingual generalisation when multilingually pre-trained vision-language models are applied to non-English data, with a large gap between (supervised) English performance and (zero-shot) cross-lingual transfer.
A Priority Map for Vision-and-Language Navigation with Trajectory Plans and Feature-Location Cues
In a busy city street, a pedestrian surrounded by distractions can pick out a single sign if it is relevant to their route.
Revisiting End-to-End Speech-to-Text Translation From Scratch
Finally, we discuss neural acoustic feature modeling, where a neural model is designed to extract acoustic features from raw speech signals directly, with the goal to simplify inductive biases and add freedom to the model in describing speech.
NusaX: Multilingual Parallel Sentiment Dataset for 10 Indonesian Local Languages
In this work, we focus on developing resources for languages in Indonesia.
NMTScore: A Multilingual Analysis of Translation-based Text Similarity Measures
Being able to rank the similarity of short text segments is an interesting bonus feature of neural machine translation.
As Little as Possible, as Much as Necessary: Detecting Over- and Undertranslations with Contrastive Conditioning
Omission and addition of content is a typical issue in neural machine translation.
Identifying Weaknesses in Machine Translation Metrics Through Minimum Bayes Risk Decoding: A Case Study for COMET
Neural metrics have achieved impressive correlation with human judgements in the evaluation of machine translation systems, but before we can safely optimise towards such metrics, we should be aware of (and ideally eliminate) biases toward bad translations that receive high scores.
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.
On the Limits of Minimal Pairs in Contrastive Evaluation
Minimal sentence pairs are frequently used to analyze the behavior of language models.
Improving Zero-shot Cross-lingual Transfer between Closely Related Languages by injecting Character-level Noise
Cross-lingual transfer between a high-resource language and its dialects or closely related language varieties should be facilitated by their similarity.
Vision Matters When It Should: Sanity Checking Multimodal Machine Translation Models
Multimodal machine translation (MMT) systems have been shown to outperform their text-only neural machine translation (NMT) counterparts when visual context is available.
Language Modeling, Lexical Translation, Reordering: The Training Process of NMT through the Lens of Classical SMT
Differently from the traditional statistical MT that decomposes the translation task into distinct separately learned components, neural machine translation uses a single neural network to model the entire translation process.
How Suitable Are Subword Segmentation Strategies for Translating Non-Concatenative Morphology?
Data-driven subword segmentation has become the default strategy for open-vocabulary machine translation and other NLP tasks, but may not be sufficiently generic for optimal learning of non-concatenative morphology.
Beyond Sentence-Level End-to-End Speech Translation: Context Helps
Document-level contextual information has shown benefits to text-based machine translation, but whether and how context helps end-to-end (E2E) speech translation (ST) is still under-studied.
Revisiting Negation in Neural Machine Translation
In this paper, we evaluate the translation of negation both automatically and manually, in English--German (EN--DE) and English--Chinese (EN--ZH).
Understanding the Properties of Minimum Bayes Risk Decoding in Neural Machine Translation
Neural Machine Translation (NMT) currently exhibits biases such as producing translations that are too short and overgenerating frequent words, and shows poor robustness to copy noise in training data or domain shift.
On Biasing Transformer Attention Towards Monotonicity
Many sequence-to-sequence tasks in natural language processing are roughly monotonic in the alignment between source and target sequence, and previous work has facilitated or enforced learning of monotonic attention behavior via specialized attention functions or pretraining.
ELITR Multilingual Live Subtitling: Demo and Strategy
This paper presents an automatic speech translation system aimed at live subtitling of conference presentations.
BlonDe: An Automatic Evaluation Metric for Document-level Machine Translation
Standard automatic metrics, e. g. BLEU, are not reliable for document-level MT evaluation.
Share or Not? Learning to Schedule Language-Specific Capacity for Multilingual Translation
Our study further verifies the trade-off between the shared capacity and LS capacity for multilingual translation.
The Impact of Text Presentation on Translator Performance
Widely used computer-aided translation (CAT) tools divide documents into segments such as sentences and arrange them in a side-by-side, spreadsheet-like view.
Understanding Pure Character-Based Neural Machine Translation: The Case of Translating Finnish into English
The attention distribution pattern shows that separators attract a lot of attention and we explore a sparse word-level attention to enforce character hidden states to capture the full word-level information.
Subword Segmentation and a Single Bridge Language Affect Zero-Shot Neural Machine Translation
A recent trend in multilingual models is to not train on parallel data between all language pairs, but have a single bridge language, e. g. English.
Detecting Word Sense Disambiguation Biases in Machine Translation for Model-Agnostic Adversarial Attacks
Word sense disambiguation is a well-known source of translation errors in NMT.
Fast Interleaved Bidirectional Sequence Generation
Instead of assuming independence between neighbouring tokens (semi-autoregressive decoding, SA), we take inspiration from bidirectional sequence generation and introduce a decoder that generates target words from the left-to-right and right-to-left directions simultaneously.
Analyzing the Source and Target Contributions to Predictions in Neural Machine Translation
We find that models trained with more data tend to rely on source information more and to have more sharp token contributions; the training process is non-monotonic with several stages of different nature.
Adaptive Feature Selection for End-to-End Speech Translation
Information in speech signals is not evenly distributed, making it an additional challenge for end-to-end (E2E) speech translation (ST) to learn to focus on informative features.
On Romanization for Model Transfer Between Scripts in Neural Machine Translation
Our results show that romanization entails information loss and is thus not always superior to simpler vocabulary transfer methods, but can improve the transfer between related languages with different scripts.
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.
On Exposure Bias, Hallucination and Domain Shift in Neural Machine Translation
In experiments on three datasets with multiple test domains, we show that exposure bias is partially to blame for hallucinations, and that training with Minimum Risk Training, which avoids exposure bias, can mitigate this.
Removing European Language Barriers with Innovative Machine Translation Technology
This paper presents our progress towards deploying a versatile communication platform in the task of highly multilingual live speech translation for conferences and remote meetings live subtitling.
Improving Massively Multilingual Neural Machine Translation and Zero-Shot Translation
Massively multilingual models for neural machine translation (NMT) are theoretically attractive, but often underperform bilingual models and deliver poor zero-shot translations.
On Sparsifying Encoder Outputs in Sequence-to-Sequence Models
Inspired by these observations, we explore the feasibility of specifying rule-based patterns that mask out encoder outputs based on information such as part-of-speech tags, word frequency and word position.
A Set of Recommendations for Assessing Human-Machine Parity in Language Translation
The quality of machine translation has increased remarkably over the past years, to the degree that it was found to be indistinguishable from professional human translation in a number of empirical investigations.
X-Stance: A Multilingual Multi-Target Dataset for Stance Detection
Unlike stance detection models that have specific target issues, we use the dataset to train a single model on all the issues.
Domain Robustness in Neural Machine Translation
Domain robustness---the generalization of models to unseen test domains---is low for both statistical (SMT) and neural machine translation (NMT).
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.
Root Mean Square Layer Normalization
RMSNorm regularizes the summed inputs to a neuron in one layer according to root mean square (RMS), giving the model re-scaling invariance property and implicit learning rate adaptation ability.
Context-Aware Monolingual Repair for Neural Machine Translation
For training, the DocRepair model requires only monolingual document-level data in the target language.
The Bottom-up Evolution of Representations in the Transformer: A Study with Machine Translation and Language Modeling Objectives
In this work, we use canonical correlation analysis and mutual information estimators to study how information flows across Transformer layers and how this process depends on the choice of learning objective.
Encoders Help You Disambiguate Word Senses in Neural Machine Translation
We find that encoder hidden states outperform word embeddings significantly which indicates that encoders adequately encode relevant information for disambiguation into hidden states.
Improving Deep Transformer with Depth-Scaled Initialization and Merged Attention
The general trend in NLP is towards increasing model capacity and performance via deeper neural networks.
Understanding Neural Machine Translation by Simplification: The Case of Encoder-free Models
In this paper, we try to understand neural machine translation (NMT) via simplifying NMT architectures and training encoder-free NMT models.
Widening the Representation Bottleneck in Neural Machine Translation with Lexical Shortcuts
The transformer is a state-of-the-art neural translation model that uses attention to iteratively refine lexical representations with information drawn from the surrounding context.
A Lightweight Recurrent Network for Sequence Modeling
We apply LRN as a drop-in replacement of existing recurrent units in several neural sequential models.
Revisiting Low-Resource Neural Machine Translation: A Case Study
It has been shown that the performance of neural machine translation (NMT) drops starkly in low-resource conditions, underperforming phrase-based statistical machine translation (PBSMT) and requiring large amounts of auxiliary data to achieve competitive results.
Low Resource Neural Machine Translation
Low-Resource Neural Machine Translation
+3
Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned
Multi-head self-attention is a key component of the Transformer, a state-of-the-art architecture for neural machine translation.
When a Good Translation is Wrong in Context: Context-Aware Machine Translation Improves on Deixis, Ellipsis, and Lexical Cohesion
Though machine translation errors caused by the lack of context beyond one sentence have long been acknowledged, the development of context-aware NMT systems is hampered by several problems.
An Analysis of Attention Mechanisms: The Case of Word Sense Disambiguation in Neural Machine Translation
Recent work has shown that the encoder-decoder attention mechanisms in neural machine translation (NMT) are different from the word alignment in statistical machine translation.
A Large-Scale Test Set for the Evaluation of Context-Aware Pronoun Translation in Neural Machine Translation
We show that, while gains in BLEU are moderate for those systems, they outperform baselines by a large margin in terms of accuracy on our contrastive test set.
Sentence Compression for Arbitrary Languages via Multilingual Pivoting
In this paper we advocate the use of bilingual corpora which are abundantly available for training sentence compression models.
The Word Sense Disambiguation Test Suite at WMT18
We evaluate all German{--}English submissions to the WMT{'}18 shared translation task, plus a number of submissions from previous years, and find that performance on the task has markedly improved compared to the 2016 WMT submissions (81{\%}→93{\%} accuracy on the WSD task).
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.
Why Self-Attention? A Targeted Evaluation of Neural Machine Translation Architectures
Recently, non-recurrent architectures (convolutional, self-attentional) have outperformed RNNs in neural machine translation.
Has Machine Translation Achieved Human Parity? A Case for Document-level Evaluation
Recent research suggests that neural machine translation achieves parity with professional human translation on the WMT Chinese--English news translation task.
Context-Aware Neural Machine Translation Learns Anaphora Resolution
Standard machine translation systems process sentences in isolation and hence ignore extra-sentential information, even though extended context can both prevent mistakes in ambiguous cases and improve translation coherence.
Evaluating Machine Translation Performance on Chinese Idioms with a Blacklist Method
Our evaluation confirms that a sizable number of idioms in our test set are mistranslated (46. 1%), that literal translation error is a common error type, and that our blacklist method is effective at identifying literal translation errors.
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.
Regularization techniques for fine-tuning in neural machine translation
We investigate techniques for supervised domain adaptation for neural machine translation where an existing model trained on a large out-of-domain dataset is adapted to a small in-domain dataset.
Image Pivoting for Learning Multilingual Multimodal Representations
In this paper we propose a model to learn multimodal multilingual representations for matching images and sentences in different languages, with the aim of advancing multilingual versions of image search and image understanding.
Deep Architectures for Neural Machine Translation
It has been shown that increasing model depth improves the quality of neural machine translation.
A parallel corpus of Python functions and documentation strings for automated code documentation and code generation
Automated documentation of programming source code and automated code generation from natural language are challenging tasks of both practical and scientific interest.
Practical Neural Machine Translation
Neural Machine Translation (NMT) has achieved new breakthroughs in machine translation in recent years.
Paraphrasing Revisited with Neural Machine Translation
Recognizing and generating paraphrases is an important component in many natural language processing applications.
The SUMMA Platform Prototype
We present the first prototype of the SUMMA Platform: an integrated platform for multilingual media monitoring.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+5
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.
How Grammatical is Character-level Neural Machine Translation? Assessing MT Quality with Contrastive Translation Pairs
Analysing translation quality in regards to specific linguistic phenomena has historically been difficult and time-consuming.
Linguistic Input Features Improve Neural Machine Translation
Neural machine translation has recently achieved impressive results, while using little in the way of external linguistic information.
Ranked #3 on
Machine Translation
on WMT2016 English-German
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
The AMU-UEDIN Submission to the WMT16 News Translation Task: Attention-based NMT Models as Feature Functions in Phrase-based SMT
For the Russian-English task, our submission achieves the top BLEU result, outperforming the best pure neural system by 1. 1 BLEU points and our own phrase-based baseline by 1. 6 BLEU.
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
Modelling and Optimizing on Syntactic N-Grams for Statistical Machine Translation
The role of language models in SMT is to promote fluent translation output, but traditional n-gram language models are unable to capture fluency phenomena between distant words, such as some morphological agreement phenomena, subcategorisation, and syntactic collocations with string-level gaps.
Zmorge: A German Morphological Lexicon Extracted from Wiktionary
We describe a method to automatically extract a German lexicon from Wiktionary that is compatible with the finite-state morphological grammar SMOR.
