Search Results for author:
Found 37 papers, 13 papers with code
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.
ParBLEU: Augmenting Metrics with Automatic Paraphrases for the WMT’20 Metrics Shared Task
We describe parBLEU, parCHRF++, and parESIM, which augment baseline metrics with automatically generated paraphrases produced by PRISM (Thompson and Post, 2020a), a multilingual neural machine translation system.
Findings of the WMT 2020 Biomedical Translation Shared Task: Basque, Italian and Russian as New Additional Languages
Machine translation of scientific abstracts and terminologies has the potential to support health professionals and biomedical researchers in some of their activities.
The University of Edinburgh-Uppsala University’s Submission to the WMT 2020 Chat Translation Task
Our baseline systems are transformer-big models that are pre-trained on the WMT’19 News Translation task and fine-tuned on pseudo-in-domain web crawled data and in-domain task data.
Le projet FREEM : ressources, outils et enjeux pour l’étude du français d’Ancien Régime (The F RE EM project: Resources, tools and challenges for the study of Ancien Régime French)
En dépit de leur qualité certaine, les ressources et outils disponibles pour l’analyse du français d’Ancien Régime ne sont plus à même de répondre aux enjeux de la recherche en linguistique et en littérature pour cette période.
Findings of the WMT 2021 Biomedical Translation Shared Task: Summaries of Animal Experiments as New Test Set
In the sixth edition of the WMT Biomedical Task, we addressed a total of eight language pairs, namely English/German, English/French, English/Spanish, English/Portuguese, English/Chinese, English/Russian, English/Italian, and English/Basque.
Document-level Neural MT: A Systematic Comparison
In this paper we provide a systematic comparison of existing and new document-level neural machine translation solutions.
Complex Labelling and Similarity Prediction in Legal Texts: Automatic Analysis of France’s Court of Cassation Rulings
The first step in the detection of divergences is to detect similar cases, which is currently done manually by experts.
From FreEM to D’AlemBERT: a Large Corpus and a Language Model for Early Modern French
anguage models for historical states of language are becoming increasingly important to allow the optimal digitisation and analysis of old textual sources.
Automatic Normalisation of Early Modern French
Spelling normalisation is a useful step in the study and analysis of historical language texts, whether it is manual analysis by experts or automatic analysis using downstream natural language processing (NLP) tools.
A Simple Method for Unsupervised Bilingual Lexicon Induction for Data-Imbalanced, Closely Related Language Pairs
Existing approaches for unsupervised bilingual lexicon induction (BLI) often depend on good quality static or contextual embeddings trained on large monolingual corpora for both languages.
Investigating Lexical Sharing in Multilingual Machine Translation for Indian Languages
Multilingual language models have shown impressive cross-lingual transfer ability across a diverse set of languages and tasks.
Investigating the Translation Performance of a Large Multilingual Language Model: the Case of BLOOM
The NLP community recently saw the release of a new large open-access multilingual language model, BLOOM (BigScience et al., 2022) covering 46 languages.
Tackling Ambiguity with Images: Improved Multimodal Machine Translation and Contrastive Evaluation
One of the major challenges of machine translation (MT) is ambiguity, which can in some cases be resolved by accompanying context such as images.
BLOOM: A 176B-Parameter Open-Access Multilingual Language Model
Large language models (LLMs) have been shown to be able to perform new tasks based on a few demonstrations or natural language instructions.
MaskEval: Weighted MLM-Based Evaluation for Text Summarization and Simplification
In text summarization and simplification, system outputs must be evaluated along multiple dimensions such as relevance, factual consistency, fluency, and grammaticality, and a wide range of possible outputs could be of high quality.
From FreEM to D'AlemBERT: a Large Corpus and a Language Model for Early Modern French
Because these historical states are at the same time more complex to process and more scarce in the corpora available, specific efforts are necessary to train natural language processing (NLP) tools adapted to the data.
Multitask Prompted Training Enables Zero-Shot Task Generalization
Large language models have recently been shown to attain reasonable zero-shot generalization on a diverse set of tasks (Brown et al., 2020).
Survey of Low-Resource Machine Translation
We present a survey covering the state of the art in low-resource machine translation research.
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.
Architecture of a Scalable, Secure and Resilient Translation Platform for Multilingual News Media
A growth in news sources makes this increasingly challenging and time-consuming but MT can help automate some aspects of this process.
A Study in Improving BLEU Reference Coverage with Diverse Automatic Paraphrasing
We investigate a long-perceived shortcoming in the typical use of BLEU: its reliance on a single reference.
Document Sub-structure in Neural Machine Translation
Current approaches to machine translation (MT) either translate sentences in isolation, disregarding the context they appear in, or model context at the level of the full document, without a notion of any internal structure the document may have.
Findings of the WMT 2019 Biomedical Translation Shared Task: Evaluation for MEDLINE Abstracts and Biomedical Terminologies
In the fourth edition of the WMT Biomedical Translation task, we considered a total of six languages, namely Chinese (zh), English (en), French (fr), German (de), Portuguese (pt), and Spanish (es).
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.
DiaBLa: A Corpus of Bilingual Spontaneous Written Dialogues for Machine Translation
We provide a preliminary analysis of the corpus to confirm that the participants' judgments reveal perceptible differences in MT quality between the two MT systems used.
Detecting context-dependent sentences in parallel corpora
In this article, we provide several approaches to the automatic identification of parallel sentences that require sentence-external linguistic context to be correctly translated.
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%).
Machine Translation, it's a question of style, innit? The case of English tag questions
In this paper, we address the problem of generating English tag questions (TQs) (e. g. it is, isn{'}t it?)
Machine Translation of Speech-Like Texts: Strategies for the Inclusion of Context
Whilst the focus of Machine Translation (MT) has for a long time been the translation of planned, written texts, more and more research is being dedicated to translating speech-like texts (informal or spontaneous discourse or dialogue).
Boosting for Efficient Model Selection for Syntactic Parsing
We present an efficient model selection method using boosting for transition-based constituency parsing.
Investigating gender adaptation for speech translation
In this paper we investigate the impact of the integration of context into dialogue translation.
Correcting and Validating Syntactic Dependency in the Spoken French Treebank Rhapsodie
The micro-syntactic annotation process, presented in this paper, includes a semi-automatic preparation of the transcription, the application of a syntactic dependency parser, transcoding of the parsing results to the Rhapsodie annotation scheme, manual correction by multiple annotators followed by a validation process, and finally the application of coherence rules that check common errors.
