b'Rico Sennrich'

research

∙ 09/13/2023

Mitigating Hallucinations and Off-target Machine Translation with Source-Contrastive and Language-Contrastive Decoding

Hallucinations and off-target translation remain unsolved problems in ma...

0 Rico Sennrich, et al. ∙

research

∙ 07/28/2023

Uncertainty in Natural Language Generation: From Theory to Applications

Recent advances of powerful Language Models have allowed Natural Languag...

0 Joris Baan, et al. ∙

research

∙ 05/22/2023

Towards Unsupervised Recognition of Semantic Differences in Related Documents

Automatically highlighting words that cause semantic differences between...

0 Jannis Vamvas, et al. ∙

research

∙ 05/18/2023

Exploiting Biased Models to De-bias Text: A Gender-Fair Rewriting Model

Natural language generation models reproduce and often amplify the biase...

0 Chantal Amrhein, et al. ∙

research

∙ 05/15/2023

What's the Meaning of Superhuman Performance in Today's NLU?

In the last five years, there has been a significant focus in Natural La...

0 Simone Tedeschi, et al. ∙

research

∙ 05/02/2023

SLTUNET: A Simple Unified Model for Sign Language Translation

Despite recent successes with neural models for sign language translatio...

0 Biao Zhang, et al. ∙

research

∙ 03/23/2023

SwissBERT: The Multilingual Language Model for Switzerland

We present SwissBERT, a masked language model created specifically for p...

0 Jannis Vamvas, et al. ∙

research

∙ 02/21/2023

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

For end-to-end speech translation, regularizing the encoder with the Con...

0 Biao Zhang, et al. ∙

research

∙ 09/07/2022

Improving the Cross-Lingual Generalisation in Visual Question Answering

While several benefits were realized for multilingual vision-language pr...

0 Farhad Nooralahzadeh, et al. ∙

research

∙ 07/24/2022

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 ...

35 Jason Armitage, et al. ∙

research

∙ 06/09/2022

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

End-to-end (E2E) speech-to-text translation (ST) often depends on pretra...

0 Biao Zhang, et al. ∙

research

∙ 05/31/2022

NusaX: Multilingual Parallel Sentiment Dataset for 10 Indonesian Local Languages

Natural language processing (NLP) has a significant impact on society vi...

5 Genta Indra Winata, et al. ∙

research

∙ 04/28/2022

NMTScore: A Multilingual Analysis of Translation-based Text Similarity Measures

Being able to rank the similarity of short text segments is an interesti...

0 Jannis Vamvas, et al. ∙

research

∙ 03/03/2022

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 tr...

0 Jannis Vamvas, et al. ∙

research

∙ 02/10/2022

Identifying Weaknesses in Machine Translation Metrics Through Minimum Bayes Risk Decoding: A Case Study for COMET

Neural metrics have achieved impressive correlation with human judgement...

0 Chantal Amrhein, et al. ∙

research

∙ 10/25/2021

Distributionally Robust Recurrent Decoders with Random Network Distillation

Neural machine learning models can successfully model language that is s...

0 Antonio Valerio Miceli Barone, et al. ∙

research

∙ 09/15/2021

On the Limits of Minimal Pairs in Contrastive Evaluation

Minimal sentence pairs are frequently used to analyze the behavior of la...

0 Jannis Vamvas, et al. ∙

research

∙ 09/14/2021

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...

6 Noëmi Aepli, et al. ∙

research

∙ 09/08/2021

Vision Matters When It Should: Sanity Checking Multimodal Machine Translation Models

Multimodal machine translation (MMT) systems have been shown to outperfo...

0 Jiaoda Li, et al. ∙

research

∙ 09/03/2021

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 tran...

12 Elena Voita, et al. ∙

research

∙ 09/02/2021

How Suitable Are Subword Segmentation Strategies for Translating Non-Concatenative Morphology?

Data-driven subword segmentation has become the default strategy for ope...

0 Chantal Amrhein, et al. ∙

research

∙ 07/26/2021

Revisiting Negation in Neural Machine Translation

In this paper, we evaluate the translation of negation both automaticall...

0 Gongbo Tang, et al. ∙

research

∙ 05/18/2021

Understanding the Properties of Minimum Bayes Risk Decoding in Neural Machine Translation

Neural Machine Translation (NMT) currently exhibits biases such as produ...

9 Mathias Müller, et al. ∙

research

∙ 04/14/2021

Sparse Attention with Linear Units

Recently, it has been argued that encoder-decoder models can be made mor...

23 Biao Zhang, et al. ∙

research

∙ 04/08/2021

On Biasing Transformer Attention Towards Monotonicity

Many sequence-to-sequence tasks in natural language processing are rough...

26 Annette Rios, et al. ∙

research

∙ 11/11/2020

The Impact of Text Presentation on Translator Performance

Widely used computer-aided translation (CAT) tools divide documents into...

0 Samuel Läubli, et al. ∙

research

∙ 11/06/2020

Understanding Pure Character-Based Neural Machine Translation: The Case of Translating Finnish into English

Recent work has shown that deeper character-based neural machine transla...

0 Gongbo Tang, et al. ∙

research

∙ 11/03/2020

Detecting Word Sense Disambiguation Biases in Machine Translation for Model-Agnostic Adversarial Attacks

Word sense disambiguation is a well-known source of translation errors i...

9 Denis Emelin, et al. ∙

research

∙ 11/03/2020

Subword Segmentation and a Single Bridge Language Affect Zero-Shot Neural Machine Translation

Zero-shot neural machine translation is an attractive goal because of th...

0 Annette Rios, et al. ∙

research

∙ 10/27/2020

Fast Interleaved Bidirectional Sequence Generation

Independence assumptions during sequence generation can speed up inferen...

1 Biao Zhang, et al. ∙

research

∙ 10/21/2020

Analyzing the Source and Target Contributions to Predictions in Neural Machine Translation

In Neural Machine Translation (and, more generally, conditional language...

7 Elena Voita, et al. ∙

research

∙ 10/16/2020

Adaptive Feature Selection for End-to-End Speech Translation

Information in speech signals is not evenly distributed, making it an ad...

15 Biao Zhang, et al. ∙

research

∙ 09/30/2020

On Romanization for Model Transfer Between Scripts in Neural Machine Translation

Transfer learning is a popular strategy to improve the quality of low-re...

0 Chantal Amrhein, et al. ∙

research

∙ 05/07/2020

On Exposure Bias, Hallucination and Domain Shift in Neural Machine Translation

The standard training algorithm in neural machine translation (NMT) suff...

0 Chaojun Wang, et al. ∙

research

∙ 04/24/2020

Improving Massively Multilingual Neural Machine Translation and Zero-Shot Translation

Massively multilingual models for neural machine translation (NMT) are t...

0 Biao Zhang, et al. ∙

research

∙ 04/24/2020

On Sparsifying Encoder Outputs in Sequence-to-Sequence Models

Sequence-to-sequence models usually transfer all encoder outputs to the ...

0 Biao Zhang, et al. ∙

research

∙ 04/03/2020

A Set of Recommendations for Assessing Human-Machine Parity in Language Translation

The quality of machine translation has increased remarkably over the pas...

2 Samuel Läubli, et al. ∙

research

∙ 03/18/2020

X-Stance: A Multilingual Multi-Target Dataset for Stance Detection

We extract a large-scale stance detection dataset from comments written ...

0 Jannis Vamvas, et al. ∙

research

∙ 11/08/2019

Domain Robustness in Neural Machine Translation

Translating text that diverges from the training domain is a key challen...

0 Mathias Müller, et al. ∙

research

∙ 11/06/2019

Domain, Translationese and Noise in Synthetic Data for Neural Machine Translation

The quality of neural machine translation can be improved by leveraging ...

0 Nikolay Bogoychev, et al. ∙

research

∙ 10/16/2019

Root Mean Square Layer Normalization

Layer normalization (LayerNorm) has been successfully applied to various...

0 Biao Zhang, et al. ∙

research

∙ 09/03/2019

Context-Aware Monolingual Repair for Neural Machine Translation

Modern sentence-level NMT systems often produce plausible translations o...

0 Elena Voita, et al. ∙

research

∙ 09/03/2019

The Bottom-up Evolution of Representations in the Transformer: A Study with Machine Translation and Language Modeling Objectives

We seek to understand how the representations of individual tokens and t...

0 Elena Voita, et al. ∙

research

∙ 08/30/2019

Encoders Help You Disambiguate Word Senses in Neural Machine Translation

Neural machine translation (NMT) has achieved new state-of-the-art perfo...

0 Gongbo Tang, et al. ∙

research

∙ 08/29/2019

Improving Deep Transformer with Depth-Scaled Initialization and Merged Attention

The general trend in NLP is towards increasing model capacity and perfor...

0 Biao Zhang, et al. ∙

research

∙ 07/18/2019

Understanding Neural Machine Translation by Simplification: The Case of Encoder-free Models

In this paper, we try to understand neural machine translation (NMT) via...

0 Gongbo Tang, et al. ∙

research

∙ 06/28/2019

Widening the Representation Bottleneck in Neural Machine Translation with Lexical Shortcuts

The transformer is a state-of-the-art neural translation model that uses...

0 Denis Emelin, et al. ∙

research

∙ 05/30/2019

A Lightweight Recurrent Network for Sequence Modeling

Recurrent networks have achieved great success on various sequential tas...

0 Biao Zhang, et al. ∙

research

∙ 05/28/2019

Revisiting Low-Resource Neural Machine Translation: A Case Study

It has been shown that the performance of neural machine translation (NM...

0 Rico Sennrich, et al. ∙

research

∙ 05/23/2019

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...

0 Elena Voita, et al. ∙

Rico Sennrich

Featured Co-authors