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

Add to Chrome

Add to Firefox

Picture for Julia Kreutzer

Julia Kreutzer

Building Machine Translation Systems for the Next Thousand Languages

May 16, 2022
Ankur Bapna, Isaac Caswell, Julia Kreutzer, Orhan Firat, Daan van Esch, Aditya Siddhant, Mengmeng Niu, Pallavi Baljekar, Xavier Garcia, Wolfgang Macherey, Theresa Breiner, Vera Axelrod, Jason Riesa, Yuan Cao, Mia Xu Chen, Klaus Macherey, Maxim Krikun, Pidong Wang, Alexander Gutkin, Apurva Shah, Yanping Huang, Zhifeng Chen, Yonghui Wu, Macduff Hughes

Figure 1 for Building Machine Translation Systems for the Next Thousand Languages

Figure 2 for Building Machine Translation Systems for the Next Thousand Languages

Figure 3 for Building Machine Translation Systems for the Next Thousand Languages

Figure 4 for Building Machine Translation Systems for the Next Thousand Languages

* V2: updated with some details from 24-language Google Translate launch in May 2022

Access Paper or Ask Questions

A Few Thousand Translations Go a Long Way! Leveraging Pre-trained Models for African News Translation

May 04, 2022
David Ifeoluwa Adelani, Jesujoba Oluwadara Alabi, Angela Fan, Julia Kreutzer, Xiaoyu Shen, Machel Reid, Dana Ruiter, Dietrich Klakow, Peter Nabende, Ernie Chang, Tajuddeen Gwadabe, Freshia Sackey, Bonaventure F. P. Dossou, Chris Chinenye Emezue, Colin Leong, Michael Beukman, Shamsuddeen Hassan Muhammad, Guyo Dub Jarso, Oreen Yousuf, Andre Niyongabo Rubungo, Gilles Hacheme, Eric Peter Wairagala, Muhammad Umair Nasir, Benjamin Ayoade Ajibade, Tunde Oluwaseyi Ajayi, Yvonne Wambui Gitau, Jade Abbott, Mohamed Ahmed, Millicent Ochieng, Anuoluwapo Aremu, Perez Ogayo, Jonathan Mukiibi, Fatoumata Ouoba Kabore, Godson Koffi Kalipe, Derguene Mbaye, Allahsera Auguste Tapo, Victoire Memdjokam Koagne, Edwin Munkoh-Buabeng, Valencia Wagner, Idris Abdulmumin, Ayodele Awokoya, Happy Buzaaba, Blessing Sibanda, Andiswa Bukula, Sam Manthalu

Figure 1 for A Few Thousand Translations Go a Long Way! Leveraging Pre-trained Models for African News Translation

Figure 2 for A Few Thousand Translations Go a Long Way! Leveraging Pre-trained Models for African News Translation

Figure 3 for A Few Thousand Translations Go a Long Way! Leveraging Pre-trained Models for African News Translation

Figure 4 for A Few Thousand Translations Go a Long Way! Leveraging Pre-trained Models for African News Translation

* Accepted to NAACL 2022

Access Paper or Ask Questions

Can Multilinguality benefit Non-autoregressive Machine Translation?

Dec 16, 2021
Sweta Agrawal, Julia Kreutzer, Colin Cherry

Figure 1 for Can Multilinguality benefit Non-autoregressive Machine Translation?

Figure 2 for Can Multilinguality benefit Non-autoregressive Machine Translation?

Figure 3 for Can Multilinguality benefit Non-autoregressive Machine Translation?

Figure 4 for Can Multilinguality benefit Non-autoregressive Machine Translation?

Access Paper or Ask Questions

Bandits Don't Follow Rules: Balancing Multi-Facet Machine Translation with Multi-Armed Bandits

Oct 13, 2021
Julia Kreutzer, David Vilar, Artem Sokolov

Figure 1 for Bandits Don't Follow Rules: Balancing Multi-Facet Machine Translation with Multi-Armed Bandits

Figure 2 for Bandits Don't Follow Rules: Balancing Multi-Facet Machine Translation with Multi-Armed Bandits

Figure 3 for Bandits Don't Follow Rules: Balancing Multi-Facet Machine Translation with Multi-Armed Bandits

Figure 4 for Bandits Don't Follow Rules: Balancing Multi-Facet Machine Translation with Multi-Armed Bandits

* EMNLP Findings 2021

Access Paper or Ask Questions

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