Search Results for author: Barry Haddow

Found 89 papers, 24 papers with code

The Samsung and University of Edinburgh’s submission to IWSLT17

no code implementations IWSLT 2017 Pawel Przybysz, Marcin Chochowski, Rico Sennrich, Barry Haddow, Alexandra Birch

This paper describes the joint submission of Samsung Research and Development, Warsaw, Poland and the University of Edinburgh team to the IWSLT MT task for TED talks.

Domain Adaptation Translation

Non-Autoregressive Machine Translation: It’s Not as Fast as it Seems

no code implementations NAACL 2022 Jindřich Helcl, Barry Haddow, Alexandra Birch

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.

Machine Translation Translation

Findings of the IWSLT 2022 Evaluation Campaign

no code implementations IWSLT (ACL) 2022 Antonios Anastasopoulos, Loïc Barrault, Luisa Bentivogli, Marcely Zanon Boito, Ondřej Bojar, Roldano Cattoni, Anna Currey, Georgiana Dinu, Kevin Duh, Maha Elbayad, Clara Emmanuel, Yannick Estève, Marcello Federico, Christian Federmann, Souhir Gahbiche, Hongyu Gong, Roman Grundkiewicz, Barry Haddow, Benjamin Hsu, Dávid Javorský, Vĕra Kloudová, Surafel Lakew, Xutai Ma, Prashant Mathur, Paul McNamee, Kenton Murray, Maria Nǎdejde, Satoshi Nakamura, Matteo Negri, Jan Niehues, Xing Niu, John Ortega, Juan Pino, Elizabeth Salesky, Jiatong Shi, Matthias Sperber, Sebastian Stüker, Katsuhito Sudoh, Marco Turchi, Yogesh Virkar, Alexander Waibel, Changhan Wang, Shinji Watanabe

The evaluation campaign of the 19th International Conference on Spoken Language Translation featured eight shared tasks: (i) Simultaneous speech translation, (ii) Offline speech translation, (iii) Speech to speech translation, (iv) Low-resource speech translation, (v) Multilingual speech translation, (vi) Dialect speech translation, (vii) Formality control for speech translation, (viii) Isometric speech translation.

Speech-to-Speech Translation Translation

Samsung and University of Edinburgh’s System for the IWSLT 2018 Low Resource MT Task

no code implementations IWSLT (EMNLP) 2018 Philip Williams, Marcin Chochowski, Pawel Przybysz, Rico Sennrich, Barry Haddow, Alexandra Birch

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.

Findings of the 2021 Conference on Machine Translation (WMT21)

no code implementations WMT (EMNLP) 2021 Farhad Akhbardeh, Arkady Arkhangorodsky, Magdalena Biesialska, Ondřej Bojar, Rajen Chatterjee, Vishrav Chaudhary, Marta R. Costa-Jussa, Cristina España-Bonet, Angela Fan, Christian Federmann, Markus Freitag, Yvette Graham, Roman Grundkiewicz, Barry Haddow, Leonie Harter, Kenneth Heafield, Christopher Homan, Matthias Huck, Kwabena Amponsah-Kaakyire, Jungo Kasai, Daniel Khashabi, Kevin Knight, Tom Kocmi, Philipp Koehn, Nicholas Lourie, Christof Monz, Makoto Morishita, Masaaki Nagata, Ajay Nagesh, Toshiaki Nakazawa, Matteo Negri, Santanu Pal, Allahsera Auguste Tapo, Marco Turchi, Valentin Vydrin, Marcos Zampieri

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.

Machine Translation Translation

Compact Speech Translation Models via Discrete Speech Units Pretraining

no code implementations29 Feb 2024 Tsz Kin Lam, Alexandra Birch, Barry Haddow

In this paper, we leverage the SSL models by pretraining smaller models on their Discrete Speech Units (DSU).

Self-Supervised Learning Translation

Prosody in Cascade and Direct Speech-to-Text Translation: a case study on Korean Wh-Phrases

no code implementations1 Feb 2024 Giulio Zhou, Tsz Kin Lam, Alexandra Birch, Barry Haddow

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.

speech-recognition Speech Recognition +2

Retrieval-augmented Multilingual Knowledge Editing

1 code implementation20 Dec 2023 Weixuan Wang, Barry Haddow, Alexandra Birch

Knowledge represented in Large Language Models (LLMs) is quite often incorrect and can also become obsolete over time.

knowledge editing Retrieval

Large Language Model Inference with Lexical Shortlisting

no code implementations16 Nov 2023 Nikolay Bogoychev, Pinzhen Chen, Barry Haddow, Alexandra Birch

Large language model (LLM) inference is computation and memory intensive, so we adapt lexical shortlisting to it hoping to improve both.

Language Modelling Large Language Model +1

Assessing the Reliability of Large Language Model Knowledge

1 code implementation15 Oct 2023 Weixuan Wang, Barry Haddow, Alexandra Birch, Wei Peng

Large language models (LLMs) have been treated as knowledge bases due to their strong performance in knowledge probing tasks.

Hallucination Knowledge Probing +3

Monolingual or Multilingual Instruction Tuning: Which Makes a Better Alpaca

1 code implementation16 Sep 2023 Pinzhen Chen, Shaoxiong Ji, Nikolay Bogoychev, Andrey Kutuzov, Barry Haddow, Kenneth Heafield

Foundational large language models (LLMs) can be instruction-tuned to perform open-domain question answering, facilitating applications like chat assistants.

Instruction Following Large Language Model +3

Iterative Translation Refinement with Large Language Models

no code implementations6 Jun 2023 Pinzhen Chen, Zhicheng Guo, Barry Haddow, Kenneth Heafield

In this paper, we propose iterative translation refinement to leverage the power of large language models for more natural translation and post-editing.

Language Modelling Large Language Model +1

When Does Monolingual Data Help Multilingual Translation: The Role of Domain and Model Scale

no code implementations23 May 2023 Christos Baziotis, Biao Zhang, Alexandra Birch, Barry Haddow

Next, we analyze the impact of scale (from 90M to 1. 6B parameters) and find it is important for both methods, particularly DAE.

Denoising Machine Translation +1

Hallucinations in Large Multilingual Translation Models

1 code implementation28 Mar 2023 Nuno M. Guerreiro, Duarte Alves, Jonas Waldendorf, Barry Haddow, Alexandra Birch, Pierre Colombo, André F. T. Martins

Large-scale multilingual machine translation systems have demonstrated remarkable ability to translate directly between numerous languages, making them increasingly appealing for real-world applications.

Language Modelling Large Language Model +2

Efficient CTC Regularization via Coarse Labels for End-to-End Speech Translation

1 code implementation21 Feb 2023 Biao Zhang, Barry Haddow, Rico Sennrich

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.


Prompting Large Language Model for Machine Translation: A Case Study

no code implementations17 Jan 2023 Biao Zhang, Barry Haddow, Alexandra Birch

Research on prompting has shown excellent performance with little or even no supervised training across many tasks.

Language Modelling Large Language Model +6

Don't Discard Fixed-Window Audio Segmentation in Speech-to-Text Translation

1 code implementation24 Oct 2022 Chantal Amrhein, Barry Haddow

For real-life applications, it is crucial that end-to-end spoken language translation models perform well on continuous audio, without relying on human-supplied segmentation.

Segmentation Speech-to-Text Translation +1

Simultaneous Translation for Unsegmented Input: A Sliding Window Approach

no code implementations18 Oct 2022 Sukanta Sen, Ondřej Bojar, Barry Haddow

In the cascaded approach to spoken language translation (SLT), the ASR output is typically punctuated and segmented into sentences before being passed to MT, since the latter is typically trained on written text.

Sentence Translation

Revisiting End-to-End Speech-to-Text Translation From Scratch

1 code implementation9 Jun 2022 Biao Zhang, Barry Haddow, Rico Sennrich

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.

speech-recognition Speech Recognition +2

Non-Autoregressive Machine Translation: It's Not as Fast as it Seems

no code implementations4 May 2022 Jindřich Helcl, Barry Haddow, Alexandra Birch

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.

Machine Translation Translation

The ELITR ECA Corpus

no code implementations15 Sep 2021 Philip Williams, Barry Haddow

We present the ELITR ECA corpus, a multilingual corpus derived from publications of the European Court of Auditors.

Sentence Translation

Beyond Sentence-Level End-to-End Speech Translation: Context Helps

1 code implementation ACL 2021 Biao Zhang, Ivan Titov, Barry Haddow, Rico Sennrich

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.

Computational Efficiency feature selection +3

Exploring Unsupervised Pretraining Objectives for Machine Translation

1 code implementation Findings (ACL) 2021 Christos Baziotis, Ivan Titov, Alexandra Birch, Barry Haddow

Unsupervised cross-lingual pretraining has achieved strong results in neural machine translation (NMT), by drastically reducing the need for large parallel data.

Language Modelling Machine Translation +3

SLTEV: Comprehensive Evaluation of Spoken Language Translation

1 code implementation EACL 2021 Ebrahim Ansari, Ond{\v{r}}ej Bojar, Barry Haddow, Mohammad Mahmoudi

SLTev reports the quality, latency, and stability of an SLT candidate output based on the time-stamped transcript and reference translation into a target language.

Machine Translation Translation

Adaptive Feature Selection for End-to-End Speech Translation

1 code implementation Findings of the Association for Computational Linguistics 2020 Biao Zhang, Ivan Titov, Barry Haddow, Rico Sennrich

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.

Data Augmentation feature selection +1

Dynamic Masking for Improved Stability in Spoken Language Translation

no code implementations30 May 2020 Yuekun Yao, Barry Haddow

For spoken language translation (SLT) in live scenarios such as conferences, lectures and meetings, it is desirable to show the translation to the user as quickly as possible, avoiding an annoying lag between speaker and translated captions.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +3

Bridging Linguistic Typology and Multilingual Machine Translation with Multi-View Language Representations

1 code implementation EMNLP 2020 Arturo Oncevay, Barry Haddow, Alexandra Birch

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.

Clustering Machine Translation +1

PMIndia -- A Collection of Parallel Corpora of Languages of India

2 code implementations27 Jan 2020 Barry Haddow, Faheem Kirefu

Parallel text is required for building high-quality machine translation (MT) systems, as well as for other multilingual NLP applications.

Machine Translation Multilingual NLP +3

Translationese in Machine Translation Evaluation

no code implementations24 Jun 2019 Yvette Graham, Barry Haddow, Philipp Koehn

Finally, we provide a comprehensive check-list for future machine translation evaluation.

Machine Translation Translation

Evaluating Discourse Phenomena in Neural Machine Translation

no code implementations NAACL 2018 Rachel Bawden, Rico Sennrich, Alexandra Birch, Barry Haddow

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 NMT +2

Regularization techniques for fine-tuning in neural machine translation

no code implementations EMNLP 2017 Antonio Valerio Miceli Barone, Barry Haddow, Ulrich Germann, Rico Sennrich

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.

Domain Adaptation L2 Regularization +4

Practical Neural Machine Translation

no code implementations EACL 2017 Rico Sennrich, Barry Haddow

Neural Machine Translation (NMT) has achieved new breakthroughs in machine translation in recent years.

Machine Translation NMT +1

HUME: Human UCCA-Based Evaluation of Machine Translation

1 code implementation EMNLP 2016 Alexandra Birch, Omri Abend, Ondrej Bojar, Barry Haddow

Human evaluation of machine translation normally uses sentence-level measures such as relative ranking or adequacy scales.

Machine Translation Sentence +1

Linguistic Input Features Improve Neural Machine Translation

1 code implementation WS 2016 Rico Sennrich, Barry Haddow

Neural machine translation has recently achieved impressive results, while using little in the way of external linguistic information.

Machine Translation Translation

Edinburgh Neural Machine Translation Systems for WMT 16

1 code implementation WS 2016 Rico Sennrich, Barry Haddow, Alexandra Birch

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.

Machine Translation Translation

Neural Machine Translation of Rare Words with Subword Units

25 code implementations ACL 2016 Rico Sennrich, Barry Haddow, Alexandra Birch

Neural machine translation (NMT) models typically operate with a fixed vocabulary, but translation is an open-vocabulary problem.

NMT Segmentation +1

Cannot find the paper you are looking for? You can Submit a new open access paper.