papers

Publications (41)

cs.CL2021

Assessing Reference-Free Peer Evaluation for Machine Translation

Sweta Agrawal, George Foster, Markus Freitag +1

Reference-free evaluation has the potential to make machine translation evaluation substantially more scalable, allowing us to pivot easily to new languages or domains. It has been…

cs.CL2020

Sentence Boundary Augmentation For Neural Machine Translation Robustness

Daniel Li, Te I, Naveen Arivazhagan +2

Neural Machine Translation (NMT) models have demonstrated strong state of the art performance on translation tasks where well-formed training and evaluation data are provided, but…

cs.CL2023

Searching for Needles in a Haystack: On the Role of Incidental Bilingualism in PaLM's Translation Capability

Eleftheria Briakou, Colin Cherry, George Foster

Large, multilingual language models exhibit surprisingly good zero- or few-shot machine translation capabilities, despite having never seen the intentionally-included translation e…

cs.CL2024

Translating Step-by-Step: Decomposing the Translation Process for Improved Translation Quality of Long-Form Texts

Eleftheria Briakou, Jiaming Luo, Colin Cherry +1

In this paper we present a step-by-step approach to long-form text translation, drawing on established processes in translation studies. Instead of viewing machine translation as a…

cs.CL2019

Thinking Slow about Latency Evaluation for Simultaneous Machine Translation

Colin Cherry, George Foster

Simultaneous machine translation attempts to translate a source sentence before it is finished being spoken, with applications to translation of spoken language for live streaming…

cs.CL2025

Gemma 3 Technical Report

Gemma Team, Aishwarya Kamath, Johan Ferret +209

We introduce Gemma 3, a multimodal addition to the Gemma family of lightweight open models, ranging in scale from 1 to 27 billion parameters. This version introduces vision underst…

cs.CL2026

TranslateGemma Technical Report

Mara Finkelstein, Isaac Caswell, Tobias Domhan +18

We present TranslateGemma, a suite of open machine translation models based on the Gemma 3 foundation models. To enhance the inherent multilingual capabilities of Gemma 3 for the t…

cs.CL2019

Monotonic Infinite Lookback Attention for Simultaneous Machine Translation

Naveen Arivazhagan, Colin Cherry, Wolfgang Macherey +5

Simultaneous machine translation begins to translate each source sentence before the source speaker is finished speaking, with applications to live and streaming scenarios. Simulta…

cs.CL2024

To Diverge or Not to Diverge: A Morphosyntactic Perspective on Machine Translation vs Human Translation

Jiaming Luo, Colin Cherry, George Foster

We conduct a large-scale fine-grained comparative analysis of machine translations (MT) against human translations (HT) through the lens of morphosyntactic divergence. Across three…

cs.CL2020

Inference Strategies for Machine Translation with Conditional Masking

Julia Kreutzer, George Foster, Colin Cherry

Conditional masked language model (CMLM) training has proven successful for non-autoregressive and semi-autoregressive sequence generation tasks, such as machine translation. Given…

cs.HC2019

Shaping the Narrative Arc: An Information-Theoretic Approach to Collaborative Dialogue

Kory W. Mathewson, Pablo Samuel Castro, Colin Cherry +2

We consider the problem of designing an artificial agent capable of interacting with humans in collaborative dialogue to produce creative, engaging narratives. In this task, the go…

cs.CL2017

A Challenge Set Approach to Evaluating Machine Translation

Pierre Isabelle, Colin Cherry, George Foster

Neural machine translation represents an exciting leap forward in translation quality. But what longstanding weaknesses does it resolve, and which remain? We address these question…

cs.CL2023

The unreasonable effectiveness of few-shot learning for machine translation

Xavier Garcia, Yamini Bansal, Colin Cherry +5

We demonstrate the potential of few-shot translation systems, trained with unpaired language data, for both high and low-resource language pairs. We show that with only 5 examples…

cs.LG2019

Lingvo: a Modular and Scalable Framework for Sequence-to-Sequence Modeling

Jonathan Shen, Patrick Nguyen, Yonghui Wu +88

Lingvo is a Tensorflow framework offering a complete solution for collaborative deep learning research, with a particular focus towards sequence-to-sequence models. Lingvo models a…

cs.CL2023

Prompting PaLM for Translation: Assessing Strategies and Performance

David Vilar, Markus Freitag, Colin Cherry +3

Large language models (LLMs) that have been trained on multilingual but not parallel text exhibit a remarkable ability to translate between languages. We probe this ability in an i…

cs.CL2019

Reinforcement Learning based Curriculum Optimization for Neural Machine Translation

Gaurav Kumar, George Foster, Colin Cherry +1

We consider the problem of making efficient use of heterogeneous training data in neural machine translation (NMT). Specifically, given a training dataset with a sentence-level fea…

cs.CL2023

XTREME-UP: A User-Centric Scarce-Data Benchmark for Under-Represented Languages

Sebastian Ruder, Jonathan H. Clark, Alexander Gutkin +24

Data scarcity is a crucial issue for the development of highly multilingual NLP systems. Yet for many under-represented languages (ULs) -- languages for which NLP re-search is part…

cs.CL2023

PaLM 2 Technical Report

Rohan Anil, Andrew M. Dai, Orhan Firat +125

We introduce PaLM 2, a new state-of-the-art language model that has better multilingual and reasoning capabilities and is more compute-efficient than its predecessor PaLM. PaLM 2 i…

cs.LG2022

Data Scaling Laws in NMT: The Effect of Noise and Architecture

Yamini Bansal, Behrooz Ghorbani, Ankush Garg +5

In this work, we study the effect of varying the architecture and training data quality on the data scaling properties of Neural Machine Translation (NMT). First, we establish that…

cs.CL2021

Can Multilinguality benefit Non-autoregressive Machine Translation?

Sweta Agrawal, Julia Kreutzer, Colin Cherry

Non-autoregressive (NAR) machine translation has recently achieved significant improvements, and now outperforms autoregressive (AR) models on some benchmarks, providing an efficie…

cs.CL2022

Leveraging unsupervised and weakly-supervised data to improve direct speech-to-speech translation

Ye Jia, Yifan Ding, Ankur Bapna +4

End-to-end speech-to-speech translation (S2ST) without relying on intermediate text representations is a rapidly emerging frontier of research. Recent works have demonstrated that…

cs.LG2021

Scaling Laws for Neural Machine Translation

Behrooz Ghorbani, Orhan Firat, Markus Freitag +5

We present an empirical study of scaling properties of encoder-decoder Transformer models used in neural machine translation (NMT). We show that cross-entropy loss as a function of…

cs.CL2019

Massively Multilingual Neural Machine Translation in the Wild: Findings and Challenges

Naveen Arivazhagan, Ankur Bapna, Orhan Firat +10

We introduce our efforts towards building a universal neural machine translation (NMT) system capable of translating between any language pair. We set a milestone towards this goal…

cs.CL2025

Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities

Gheorghe Comanici, Eric Bieber, Mike Schaekermann +3431

In this report, we introduce the Gemini 2.X model family: Gemini 2.5 Pro and Gemini 2.5 Flash, as well as our earlier Gemini 2.0 Flash and Flash-Lite models. Gemini 2.5 Pro is our…

cs.CL2020

Re-Translation Strategies For Long Form, Simultaneous, Spoken Language Translation

Naveen Arivazhagan, Colin Cherry, Te I +3

We investigate the problem of simultaneous machine translation of long-form speech content. We target a continuous speech-to-text scenario, generating translated captions for a liv…

cs.CL2025

SSA-COMET: Do LLMs Outperform Learned Metrics in Evaluating MT for Under-Resourced African Languages?

Senyu Li, Jiayi Wang, Felermino D. M. A. Ali +7

Evaluating machine translation (MT) quality for under-resourced African languages remains a significant challenge, as existing metrics often suffer from limited language coverage a…

cs.CL2024

On the Implications of Verbose LLM Outputs: A Case Study in Translation Evaluation

Eleftheria Briakou, Zhongtao Liu, Colin Cherry +1

This paper investigates the impact of verbose LLM translations on evaluation. We first demonstrate the prevalence of this behavior across several LLM outputs drawn from the WMT 202…

cs.CL2022

mSLAM: Massively multilingual joint pre-training for speech and text

Ankur Bapna, Colin Cherry, Yu Zhang +6

We present mSLAM, a multilingual Speech and LAnguage Model that learns cross-lingual cross-modal representations of speech and text by pre-training jointly on large amounts of unla…

cs.CL2020

Re-translation versus Streaming for Simultaneous Translation

Naveen Arivazhagan, Colin Cherry, Wolfgang Macherey +1

There has been great progress in improving streaming machine translation, a simultaneous paradigm where the system appends to a growing hypothesis as more source content becomes av…

cs.CL2024

Quality-Aware Translation Models: Efficient Generation and Quality Estimation in a Single Model

Christian Tomani, David Vilar, Markus Freitag +5

Maximum-a-posteriori (MAP) decoding is the most widely used decoding strategy for neural machine translation (NMT) models. The underlying assumption is that model probability corre…

cs.CL2022

XTREME-S: Evaluating Cross-lingual Speech Representations

Alexis Conneau, Ankur Bapna, Yu Zhang +16

We introduce XTREME-S, a new benchmark to evaluate universal cross-lingual speech representations in many languages. XTREME-S covers four task families: speech recognition, classif…

cs.CL2026

Are Multilingual Models Actually Improving? Isolating True Cross-Lingual Transfer

Prasoon Bajpai, Eleftheria Briakou, Colin Cherry +2

Cross-lingual transfer is a model's ability to generalize capabilities from well-represented source languages to under-represented target languages. Existing measures of a model's…

cs.LG2018

Efficient Sequence Labeling with Actor-Critic Training

Saeed Najafi, Colin Cherry, Grzegorz Kondrak

Neural approaches to sequence labeling often use a Conditional Random Field (CRF) to model their output dependencies, while Recurrent Neural Networks (RNN) are used for the same pu…

cs.CL2025

Overestimation in LLM Evaluation: A Controlled Large-Scale Study on Data Contamination's Impact on Machine Translation

Muhammed Yusuf Kocyigit, Eleftheria Briakou, Daniel Deutsch +3

Data contamination -- the accidental consumption of evaluation examples within the pre-training data -- can undermine the validity of evaluation benchmarks. In this paper, we prese…

cs.CL2017

End-to-End Multi-View Networks for Text Classification

Hongyu Guo, Colin Cherry, Jiang Su

We propose a multi-view network for text classification. Our method automatically creates various views of its input text, each taking the form of soft attention weights that distr…

cs.CL2025

Leveraging Domain Knowledge at Inference Time for LLM Translation: Retrieval versus Generation

Bryan Li, Jiaming Luo, Eleftheria Briakou +1

While large language models (LLMs) have been increasingly adopted for machine translation (MT), their performance for specialist domains such as medicine and law remains an open ch…

cs.CL2024

Don't Throw Away Data: Better Sequence Knowledge Distillation

Jun Wang, Eleftheria Briakou, Hamid Dadkhahi +3

A critical component in knowledge distillation is the means of coupling the teacher and student. The predominant sequence knowledge distillation method involves supervised learning…

cs.CL2025

SMOL: Professionally translated parallel data for 115 under-represented languages

Isaac Caswell, Elizabeth Nielsen, Jiaming Luo +23

We open-source SMOL (Set of Maximal Overall Leverage), a suite of training data to unlock machine translation for low-resource languages. SMOL has been translated into 124 (and gro…

cs.CL2020

Human-Paraphrased References Improve Neural Machine Translation

Markus Freitag, George Foster, David Grangier +1

Automatic evaluation comparing candidate translations to human-generated paraphrases of reference translations has recently been proposed by Freitag et al. When used in place of or…

cs.CL2018

Revisiting Character-Based Neural Machine Translation with Capacity and Compression

Colin Cherry, George Foster, Ankur Bapna +2

Translating characters instead of words or word-fragments has the potential to simplify the processing pipeline for neural machine translation (NMT), and improve results by elimina…

cs.CL2024

When Scaling Meets LLM Finetuning: The Effect of Data, Model and Finetuning Method

Biao Zhang, Zhongtao Liu, Colin Cherry +1

While large language models (LLMs) often adopt finetuning to unlock their capabilities for downstream applications, our understanding on the inductive biases (especially the scalin…