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 Manuel Mager

Manuel Mager

BPE vs. Morphological Segmentation: A Case Study on Machine Translation of Four Polysynthetic Languages


Mar 16, 2022
Manuel Mager, Arturo Oncevay, Elisabeth Mager, Katharina Kann, Ngoc Thang Vu

Figure 1 for BPE vs. Morphological Segmentation: A Case Study on Machine Translation of Four Polysynthetic Languages
Figure 2 for BPE vs. Morphological Segmentation: A Case Study on Machine Translation of Four Polysynthetic Languages
Figure 3 for BPE vs. Morphological Segmentation: A Case Study on Machine Translation of Four Polysynthetic Languages
Figure 4 for BPE vs. Morphological Segmentation: A Case Study on Machine Translation of Four Polysynthetic Languages
* Accepted to Findings of ACL 2022 
  Access Paper or Ask Questions

IMS' Systems for the IWSLT 2021 Low-Resource Speech Translation Task


Jun 30, 2021
Pavel Denisov, Manuel Mager, Ngoc Thang Vu

Figure 1 for IMS' Systems for the IWSLT 2021 Low-Resource Speech Translation Task
Figure 2 for IMS' Systems for the IWSLT 2021 Low-Resource Speech Translation Task
Figure 3 for IMS' Systems for the IWSLT 2021 Low-Resource Speech Translation Task
Figure 4 for IMS' Systems for the IWSLT 2021 Low-Resource Speech Translation Task
* IWSLT 2021 
  Access Paper or Ask Questions

AmericasNLI: Evaluating Zero-shot Natural Language Understanding of Pretrained Multilingual Models in Truly Low-resource Languages


Apr 18, 2021
Abteen Ebrahimi, Manuel Mager, Arturo Oncevay, Vishrav Chaudhary, Luis Chiruzzo, Angela Fan, John Ortega, Ricardo Ramos, Annette Rios, Ivan Vladimir, Gustavo A. Giménez-Lugo, Elisabeth Mager, Graham Neubig, Alexis Palmer, Rolando A. Coto Solano, Ngoc Thang Vu, Katharina Kann

Figure 1 for AmericasNLI: Evaluating Zero-shot Natural Language Understanding of Pretrained Multilingual Models in Truly Low-resource Languages
Figure 2 for AmericasNLI: Evaluating Zero-shot Natural Language Understanding of Pretrained Multilingual Models in Truly Low-resource Languages
Figure 3 for AmericasNLI: Evaluating Zero-shot Natural Language Understanding of Pretrained Multilingual Models in Truly Low-resource Languages
Figure 4 for AmericasNLI: Evaluating Zero-shot Natural Language Understanding of Pretrained Multilingual Models in Truly Low-resource Languages

  Access Paper or Ask Questions

Tackling the Low-resource Challenge for Canonical Segmentation


Oct 06, 2020
Manuel Mager, Özlem Çetinoğlu, Katharina Kann

Figure 1 for Tackling the Low-resource Challenge for Canonical Segmentation
Figure 2 for Tackling the Low-resource Challenge for Canonical Segmentation
Figure 3 for Tackling the Low-resource Challenge for Canonical Segmentation
Figure 4 for Tackling the Low-resource Challenge for Canonical Segmentation
* Accepted to EMNLP 2020 
  Access Paper or Ask Questions

GPT-too: A language-model-first approach for AMR-to-text generation


May 27, 2020
Manuel Mager, Ramon Fernandez Astudillo, Tahira Naseem, Md Arafat Sultan, Young-Suk Lee, Radu Florian, Salim Roukos

Figure 1 for GPT-too: A language-model-first approach for AMR-to-text generation
Figure 2 for GPT-too: A language-model-first approach for AMR-to-text generation
Figure 3 for GPT-too: A language-model-first approach for AMR-to-text generation
Figure 4 for GPT-too: A language-model-first approach for AMR-to-text generation
* Paper accepted to the Annual Meeting of the Association for Computational Linguistics (ACL 2020) 
  Access Paper or Ask Questions

The IMS-CUBoulder System for the SIGMORPHON 2020 Shared Task on Unsupervised Morphological Paradigm Completion


May 25, 2020
Manuel Mager, Katharina Kann

Figure 1 for The IMS-CUBoulder System for the SIGMORPHON 2020 Shared Task on Unsupervised Morphological Paradigm Completion
Figure 2 for The IMS-CUBoulder System for the SIGMORPHON 2020 Shared Task on Unsupervised Morphological Paradigm Completion
Figure 3 for The IMS-CUBoulder System for the SIGMORPHON 2020 Shared Task on Unsupervised Morphological Paradigm Completion
Figure 4 for The IMS-CUBoulder System for the SIGMORPHON 2020 Shared Task on Unsupervised Morphological Paradigm Completion

  Access Paper or Ask Questions

Subword-Level Language Identification for Intra-Word Code-Switching


Apr 03, 2019
Manuel Mager, Özlem Çetinoğlu, Katharina Kann

Figure 1 for Subword-Level Language Identification for Intra-Word Code-Switching
Figure 2 for Subword-Level Language Identification for Intra-Word Code-Switching
Figure 3 for Subword-Level Language Identification for Intra-Word Code-Switching
Figure 4 for Subword-Level Language Identification for Intra-Word Code-Switching
* NAACL-HLT 2019 
  Access Paper or Ask Questions

Lost in Translation: Analysis of Information Loss During Machine Translation Between Polysynthetic and Fusional Languages


Jul 01, 2018
Manuel Mager, Elisabeth Mager, Alfonso Medina-Urrea, Ivan Meza, Katharina Kann

Figure 1 for Lost in Translation: Analysis of Information Loss During Machine Translation Between Polysynthetic and Fusional Languages
Figure 2 for Lost in Translation: Analysis of Information Loss During Machine Translation Between Polysynthetic and Fusional Languages
* To appear in "All Together Now? Computational Modeling of Polysynthetic Languages" Workshop, at COLING 2018 
  Access Paper or Ask Questions

Challenges of language technologies for the indigenous languages of the Americas


Jun 12, 2018
Manuel Mager, Ximena Gutierrez-Vasques, Gerardo Sierra, Ivan Meza

Figure 1 for Challenges of language technologies for the indigenous languages of the Americas
Figure 2 for Challenges of language technologies for the indigenous languages of the Americas
Figure 3 for Challenges of language technologies for the indigenous languages of the Americas
* In Proceedings of the 27th International Conference on Computational Linguistics (COLING 2018) 
  Access Paper or Ask Questions

Fortification of Neural Morphological Segmentation Models for Polysynthetic Minimal-Resource Languages


Apr 17, 2018
Katharina Kann, Manuel Mager, Ivan Meza-Ruiz, Hinrich Schütze

Figure 1 for Fortification of Neural Morphological Segmentation Models for Polysynthetic Minimal-Resource Languages
Figure 2 for Fortification of Neural Morphological Segmentation Models for Polysynthetic Minimal-Resource Languages
Figure 3 for Fortification of Neural Morphological Segmentation Models for Polysynthetic Minimal-Resource Languages
Figure 4 for Fortification of Neural Morphological Segmentation Models for Polysynthetic Minimal-Resource Languages
* Long Paper, 16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies 
  Access Paper or Ask Questions