Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox
Picture for Julia Kreutzer

Julia Kreutzer

The Low-Resource Double Bind: An Empirical Study of Pruning for Low-Resource Machine Translation


Oct 06, 2021
Orevaoghene Ahia, Julia Kreutzer, Sara Hooker

Figure 1 for The Low-Resource Double Bind: An Empirical Study of Pruning for Low-Resource Machine Translation
Figure 2 for The Low-Resource Double Bind: An Empirical Study of Pruning for Low-Resource Machine Translation
Figure 3 for The Low-Resource Double Bind: An Empirical Study of Pruning for Low-Resource Machine Translation
Figure 4 for The Low-Resource Double Bind: An Empirical Study of Pruning for Low-Resource Machine Translation
* Accepted to Findings of EMNLP 2021 
  Access Paper or Ask Questions

Evaluating Multiway Multilingual NMT in the Turkic Languages


Sep 13, 2021
Jamshidbek Mirzakhalov, Anoop Babu, Aigiz Kunafin, Ahsan Wahab, Behzod Moydinboyev, Sardana Ivanova, Mokhiyakhon Uzokova, Shaxnoza Pulatova, Duygu Ataman, Julia Kreutzer, Francis Tyers, Orhan Firat, John Licato, Sriram Chellappan

Figure 1 for Evaluating Multiway Multilingual NMT in the Turkic Languages
Figure 2 for Evaluating Multiway Multilingual NMT in the Turkic Languages
Figure 3 for Evaluating Multiway Multilingual NMT in the Turkic Languages
Figure 4 for Evaluating Multiway Multilingual NMT in the Turkic Languages
* 9 pages, 3 figures, 7 tables. To be presented at WMT 2021 
  Access Paper or Ask Questions

Modelling Latent Translations for Cross-Lingual Transfer


Jul 23, 2021
Edoardo Maria Ponti, Julia Kreutzer, Ivan Vulić, Siva Reddy

Figure 1 for Modelling Latent Translations for Cross-Lingual Transfer
Figure 2 for Modelling Latent Translations for Cross-Lingual Transfer
Figure 3 for Modelling Latent Translations for Cross-Lingual Transfer
Figure 4 for Modelling Latent Translations for Cross-Lingual Transfer

  Access Paper or Ask Questions

Revisiting the Weaknesses of Reinforcement Learning for Neural Machine Translation


Jun 16, 2021
Samuel Kiegeland, Julia Kreutzer

Figure 1 for Revisiting the Weaknesses of Reinforcement Learning for Neural Machine Translation
Figure 2 for Revisiting the Weaknesses of Reinforcement Learning for Neural Machine Translation
Figure 3 for Revisiting the Weaknesses of Reinforcement Learning for Neural Machine Translation
Figure 4 for Revisiting the Weaknesses of Reinforcement Learning for Neural Machine Translation
* North American Chapter of the Association for Computational Linguistics, 2021, 1673-1681 
  Access Paper or Ask Questions

Quality at a Glance: An Audit of Web-Crawled Multilingual Datasets


Mar 22, 2021
Isaac Caswell, Julia Kreutzer, Lisa Wang, Ahsan Wahab, Daan van Esch, Nasanbayar Ulzii-Orshikh, Allahsera Tapo, Nishant Subramani, Artem Sokolov, Claytone Sikasote, Monang Setyawan, Supheakmungkol Sarin, Sokhar Samb, Benoît Sagot, Clara Rivera, Annette Rios, Isabel Papadimitriou, Salomey Osei, Pedro Javier Ortiz Suárez, Iroro Orife, Kelechi Ogueji, Rubungo Andre Niyongabo, Toan Q. Nguyen, Mathias Müller, André Müller, Shamsuddeen Hassan Muhammad, Nanda Muhammad, Ayanda Mnyakeni, Jamshidbek Mirzakhalov, Tapiwanashe Matangira, Colin Leong, Nze Lawson, Sneha Kudugunta, Yacine Jernite, Mathias Jenny, Orhan Firat, Bonaventure F. P. Dossou, Sakhile Dlamini, Nisansa de Silva, Sakine Çabuk Ballı, Stella Biderman, Alessia Battisti, Ahmed Baruwa, Ankur Bapna, Pallavi Baljekar, Israel Abebe Azime, Ayodele Awokoya, Duygu Ataman, Orevaoghene Ahia, Oghenefego Ahia, Sweta Agrawal, Mofetoluwa Adeyemi

Figure 1 for Quality at a Glance: An Audit of Web-Crawled Multilingual Datasets
Figure 2 for Quality at a Glance: An Audit of Web-Crawled Multilingual Datasets
Figure 3 for Quality at a Glance: An Audit of Web-Crawled Multilingual Datasets
Figure 4 for Quality at a Glance: An Audit of Web-Crawled Multilingual Datasets
* 10 pages paper; 10 pages appendix; AfricaNLP 2021 
  Access Paper or Ask Questions

MasakhaNER: Named Entity Recognition for African Languages


Mar 22, 2021
David Ifeoluwa Adelani, Jade Abbott, Graham Neubig, Daniel D'souza, Julia Kreutzer, Constantine Lignos, Chester Palen-Michel, Happy Buzaaba, Shruti Rijhwani, Sebastian Ruder, Stephen Mayhew, Israel Abebe Azime, Shamsuddeen Muhammad, Chris Chinenye Emezue, Joyce Nakatumba-Nabende, Perez Ogayo, Anuoluwapo Aremu, Catherine Gitau, Derguene Mbaye, Jesujoba Alabi, Seid Muhie Yimam, Tajuddeen Gwadabe, Ignatius Ezeani, Rubungo Andre Niyongabo, Jonathan Mukiibi, Verrah Otiende, Iroro Orife, Davis David, Samba Ngom, Tosin Adewumi, Paul Rayson, Mofetoluwa Adeyemi, Gerald Muriuki, Emmanuel Anebi, Chiamaka Chukwuneke, Nkiruka Odu, Eric Peter Wairagala, Samuel Oyerinde, Clemencia Siro, Tobius Saul Bateesa, Temilola Oloyede, Yvonne Wambui, Victor Akinode, Deborah Nabagereka, Maurice Katusiime, Ayodele Awokoya, Mouhamadane MBOUP, Dibora Gebreyohannes, Henok Tilaye, Kelechi Nwaike, Degaga Wolde, Abdoulaye Faye, Blessing Sibanda, Orevaoghene Ahia, Bonaventure F. P. Dossou, Kelechi Ogueji, Thierno Ibrahima DIOP, Abdoulaye Diallo, Adewale Akinfaderin, Tendai Marengereke, Salomey Osei

Figure 1 for MasakhaNER: Named Entity Recognition for African Languages
Figure 2 for MasakhaNER: Named Entity Recognition for African Languages
Figure 3 for MasakhaNER: Named Entity Recognition for African Languages
Figure 4 for MasakhaNER: Named Entity Recognition for African Languages
* Accepted at the AfricaNLP Workshop @EACL 2021 
  Access Paper or Ask Questions

Neural Machine Translation for Extremely Low-Resource African Languages: A Case Study on Bambara


Nov 10, 2020
Allahsera Auguste Tapo, Bakary Coulibaly, Sébastien Diarra, Christopher Homan, Julia Kreutzer, Sarah Luger, Arthur Nagashima, Marcos Zampieri, Michael Leventhal

Figure 1 for Neural Machine Translation for Extremely Low-Resource African Languages: A Case Study on Bambara
Figure 2 for Neural Machine Translation for Extremely Low-Resource African Languages: A Case Study on Bambara
Figure 3 for Neural Machine Translation for Extremely Low-Resource African Languages: A Case Study on Bambara
Figure 4 for Neural Machine Translation for Extremely Low-Resource African Languages: A Case Study on Bambara

  Access Paper or Ask Questions

Learning from Human Feedback: Challenges for Real-World Reinforcement Learning in NLP


Nov 06, 2020
Julia Kreutzer, Stefan Riezler, Carolin Lawrence

* To appear in the Challenges of Real-World RL Workshop at NeurIPS 2020 
  Access Paper or Ask Questions

KINNEWS and KIRNEWS: Benchmarking Cross-Lingual Text Classification for Kinyarwanda and Kirundi


Oct 23, 2020
Rubungo Andre Niyongabo, Hong Qu, Julia Kreutzer, Li Huang

Figure 1 for KINNEWS and KIRNEWS: Benchmarking Cross-Lingual Text Classification for Kinyarwanda and Kirundi
Figure 2 for KINNEWS and KIRNEWS: Benchmarking Cross-Lingual Text Classification for Kinyarwanda and Kirundi
Figure 3 for KINNEWS and KIRNEWS: Benchmarking Cross-Lingual Text Classification for Kinyarwanda and Kirundi
Figure 4 for KINNEWS and KIRNEWS: Benchmarking Cross-Lingual Text Classification for Kinyarwanda and Kirundi
* COLING 2020 
  Access Paper or Ask Questions

Inference Strategies for Machine Translation with Conditional Masking


Oct 20, 2020
Julia Kreutzer, George Foster, Colin Cherry

Figure 1 for Inference Strategies for Machine Translation with Conditional Masking
Figure 2 for Inference Strategies for Machine Translation with Conditional Masking
Figure 3 for Inference Strategies for Machine Translation with Conditional Masking
Figure 4 for Inference Strategies for Machine Translation with Conditional Masking
* EMNLP 2020, updated Fig 3 
  Access Paper or Ask Questions

Participatory Research for Low-resourced Machine Translation: A Case Study in African Languages


Oct 05, 2020
Wilhelmina Nekoto, Vukosi Marivate, Tshinondiwa Matsila, Timi Fasubaa, Tajudeen Kolawole, Taiwo Fagbohungbe, Solomon Oluwole Akinola, Shamsuddee Hassan Muhammad, Salomon Kabongo, Salomey Osei, Sackey Freshia, Rubungo Andre Niyongabo, Ricky Macharm, Perez Ogayo, Orevaoghene Ahia, Musie Meressa, Mofe Adeyemi, Masabata Mokgesi-Selinga, Lawrence Okegbemi, Laura Jane Martinus, Kolawole Tajudeen, Kevin Degila, Kelechi Ogueji, Kathleen Siminyu, Julia Kreutzer, Jason Webster, Jamiil Toure Ali, Jade Abbott, Iroro Orife, Ignatius Ezeani, Idris Abdulkabir Dangana, Herman Kamper, Hady Elsahar, Goodness Duru, Ghollah Kioko, Espoir Murhabazi, Elan van Biljon, Daniel Whitenack, Christopher Onyefuluchi, Chris Emezue, Bonaventure Dossou, Blessing Sibanda, Blessing Itoro Bassey, Ayodele Olabiyi, Arshath Ramkilowan, Alp Öktem, Adewale Akinfaderin, Abdallah Bashir

Figure 1 for Participatory Research for Low-resourced Machine Translation: A Case Study in African Languages
Figure 2 for Participatory Research for Low-resourced Machine Translation: A Case Study in African Languages
Figure 3 for Participatory Research for Low-resourced Machine Translation: A Case Study in African Languages
Figure 4 for Participatory Research for Low-resourced Machine Translation: A Case Study in African Languages
* Findings of EMNLP 2020 
  Access Paper or Ask Questions

Correct Me If You Can: Learning from Error Corrections and Markings


Apr 23, 2020
Julia Kreutzer, Nathaniel Berger, Stefan Riezler

Figure 1 for Correct Me If You Can: Learning from Error Corrections and Markings
Figure 2 for Correct Me If You Can: Learning from Error Corrections and Markings
Figure 3 for Correct Me If You Can: Learning from Error Corrections and Markings
Figure 4 for Correct Me If You Can: Learning from Error Corrections and Markings
* To appear at EAMT 2020 (Research Track) 
  Access Paper or Ask Questions

On Optimal Transformer Depth for Low-Resource Language Translation


Apr 14, 2020
Elan van Biljon, Arnu Pretorius, Julia Kreutzer

Figure 1 for On Optimal Transformer Depth for Low-Resource Language Translation
Figure 2 for On Optimal Transformer Depth for Low-Resource Language Translation
Figure 3 for On Optimal Transformer Depth for Low-Resource Language Translation
Figure 4 for On Optimal Transformer Depth for Low-Resource Language Translation

  Access Paper or Ask Questions

On optimal transformer depth for low-resource language translation


Apr 09, 2020
Elan van Biljon, Arnu Pretorius, Julia Kreutzer

Figure 1 for On optimal transformer depth for low-resource language translation
Figure 2 for On optimal transformer depth for low-resource language translation
Figure 3 for On optimal transformer depth for low-resource language translation
Figure 4 for On optimal transformer depth for low-resource language translation

  Access Paper or Ask Questions

Masakhane -- Machine Translation For Africa


Mar 13, 2020
Iroro Orife, Julia Kreutzer, Blessing Sibanda, Daniel Whitenack, Kathleen Siminyu, Laura Martinus, Jamiil Toure Ali, Jade Abbott, Vukosi Marivate, Salomon Kabongo, Musie Meressa, Espoir Murhabazi, Orevaoghene Ahia, Elan van Biljon, Arshath Ramkilowan, Adewale Akinfaderin, Alp Öktem, Wole Akin, Ghollah Kioko, Kevin Degila, Herman Kamper, Bonaventure Dossou, Chris Emezue, Kelechi Ogueji, Abdallah Bashir

Figure 1 for Masakhane -- Machine Translation For Africa
* Accepted for the AfricaNLP Workshop, ICLR 2020 
  Access Paper or Ask Questions

Joey NMT: A Minimalist NMT Toolkit for Novices


Jul 29, 2019
Julia Kreutzer, Joost Bastings, Stefan Riezler

Figure 1 for Joey NMT: A Minimalist NMT Toolkit for Novices
Figure 2 for Joey NMT: A Minimalist NMT Toolkit for Novices
Figure 3 for Joey NMT: A Minimalist NMT Toolkit for Novices
Figure 4 for Joey NMT: A Minimalist NMT Toolkit for Novices

  Access Paper or Ask Questions

Self-Regulated Interactive Sequence-to-Sequence Learning


Jul 11, 2019
Julia Kreutzer, Stefan Riezler

Figure 1 for Self-Regulated Interactive Sequence-to-Sequence Learning
Figure 2 for Self-Regulated Interactive Sequence-to-Sequence Learning
Figure 3 for Self-Regulated Interactive Sequence-to-Sequence Learning
Figure 4 for Self-Regulated Interactive Sequence-to-Sequence Learning
* ACL 2019 
  Access Paper or Ask Questions

Learning to Segment Inputs for NMT Favors Character-Level Processing


Nov 05, 2018
Julia Kreutzer, Artem Sokolov

Figure 1 for Learning to Segment Inputs for NMT Favors Character-Level Processing
Figure 2 for Learning to Segment Inputs for NMT Favors Character-Level Processing
Figure 3 for Learning to Segment Inputs for NMT Favors Character-Level Processing
Figure 4 for Learning to Segment Inputs for NMT Favors Character-Level Processing
* Technical report for IWSLT 2018 paper 
  Access Paper or Ask Questions

Reliability and Learnability of Human Bandit Feedback for Sequence-to-Sequence Reinforcement Learning


Jul 19, 2018
Julia Kreutzer, Joshua Uyheng, Stefan Riezler

Figure 1 for Reliability and Learnability of Human Bandit Feedback for Sequence-to-Sequence Reinforcement Learning
Figure 2 for Reliability and Learnability of Human Bandit Feedback for Sequence-to-Sequence Reinforcement Learning
Figure 3 for Reliability and Learnability of Human Bandit Feedback for Sequence-to-Sequence Reinforcement Learning
Figure 4 for Reliability and Learnability of Human Bandit Feedback for Sequence-to-Sequence Reinforcement Learning
* Citation fix, added figure in appendix 
  Access Paper or Ask Questions

Explaining and Generalizing Back-Translation through Wake-Sleep


Jun 12, 2018
Ryan Cotterell, Julia Kreutzer

Figure 1 for Explaining and Generalizing Back-Translation through Wake-Sleep
Figure 2 for Explaining and Generalizing Back-Translation through Wake-Sleep
Figure 3 for Explaining and Generalizing Back-Translation through Wake-Sleep

  Access Paper or Ask Questions

A Reinforcement Learning Approach to Interactive-Predictive Neural Machine Translation


Jun 05, 2018
Tsz Kin Lam, Julia Kreutzer, Stefan Riezler

Figure 1 for A Reinforcement Learning Approach to Interactive-Predictive Neural Machine Translation
Figure 2 for A Reinforcement Learning Approach to Interactive-Predictive Neural Machine Translation
Figure 3 for A Reinforcement Learning Approach to Interactive-Predictive Neural Machine Translation
Figure 4 for A Reinforcement Learning Approach to Interactive-Predictive Neural Machine Translation
* Published at EAMT 2018; Updated algorithm 
  Access Paper or Ask Questions

Can Neural Machine Translation be Improved with User Feedback?


Apr 16, 2018
Julia Kreutzer, Shahram Khadivi, Evgeny Matusov, Stefan Riezler

Figure 1 for Can Neural Machine Translation be Improved with User Feedback?
Figure 2 for Can Neural Machine Translation be Improved with User Feedback?
Figure 3 for Can Neural Machine Translation be Improved with User Feedback?
Figure 4 for Can Neural Machine Translation be Improved with User Feedback?
* Accepted at NAACL-HLT 2018 (Industry Track) 
  Access Paper or Ask Questions

A Shared Task on Bandit Learning for Machine Translation


Jul 27, 2017
Artem Sokolov, Julia Kreutzer, Kellen Sunderland, Pavel Danchenko, Witold Szymaniak, Hagen Fürstenau, Stefan Riezler

Figure 1 for A Shared Task on Bandit Learning for Machine Translation
Figure 2 for A Shared Task on Bandit Learning for Machine Translation
Figure 3 for A Shared Task on Bandit Learning for Machine Translation
Figure 4 for A Shared Task on Bandit Learning for Machine Translation
* Conference on Machine Translation (WMT) 2017 
  Access Paper or Ask Questions

Bandit Structured Prediction for Neural Sequence-to-Sequence Learning


Apr 21, 2017
Julia Kreutzer, Artem Sokolov, Stefan Riezler

Figure 1 for Bandit Structured Prediction for Neural Sequence-to-Sequence Learning
Figure 2 for Bandit Structured Prediction for Neural Sequence-to-Sequence Learning
Figure 3 for Bandit Structured Prediction for Neural Sequence-to-Sequence Learning
Figure 4 for Bandit Structured Prediction for Neural Sequence-to-Sequence Learning
* To appear in ACL 2017 
  Access Paper or Ask Questions

Stochastic Structured Prediction under Bandit Feedback


Nov 02, 2016
Artem Sokolov, Julia Kreutzer, Christopher Lo, Stefan Riezler

Figure 1 for Stochastic Structured Prediction under Bandit Feedback
Figure 2 for Stochastic Structured Prediction under Bandit Feedback
* 30th Conference on Neural Information Processing Systems (NIPS 2016), Barcelona, Spain 
  Access Paper or Ask Questions