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 Dietrich Klakow

Meta Self-Refinement for Robust Learning with Weak Supervision


May 15, 2022
Dawei Zhu, Xiaoyu Shen, Michael A. Hedderich, Dietrich Klakow


  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

* Accepted to NAACL 2022 

  Access Paper or Ask Questions

Placing M-Phasis on the Plurality of Hate: A Feature-Based Corpus of Hate Online


Apr 28, 2022
Dana Ruiter, Liane Reiners, Ashwin Geet D'Sa, Thomas Kleinbauer, Dominique Fohr, Irina Illina, Dietrich Klakow, Christian Schemer, Angeliki Monnier

* 14 pages, 4 figures, accepted at LREC 2022 (Full Paper) 

  Access Paper or Ask Questions

MCSE: Multimodal Contrastive Learning of Sentence Embeddings


Apr 22, 2022
Miaoran Zhang, Marius Mosbach, David Ifeoluwa Adelani, Michael A. Hedderich, Dietrich Klakow

* Accepted by NAACL 2022 main conference (short paper), 11 pages 

  Access Paper or Ask Questions

Is BERT Robust to Label Noise? A Study on Learning with Noisy Labels in Text Classification


Apr 20, 2022
Dawei Zhu, Michael A. Hedderich, Fangzhou Zhai, David Ifeoluwa Adelani, Dietrich Klakow

* Accepted at Workshop on Insights from Negative Results in NLP 2022 @ACL 2022 

  Access Paper or Ask Questions

Knowledge Base Index Compression via Dimensionality and Precision Reduction


Apr 18, 2022
Vilém Zouhar, Marius Mosbach, Miaoran Zhang, Dietrich Klakow

* To be presented at Spa-NLP workshop at ACL 2022 

  Access Paper or Ask Questions

Multilingual Language Model Adaptive Fine-Tuning: A Study on African Languages


Apr 13, 2022
Jesujoba O. Alabi, David Ifeoluwa Adelani, Marius Mosbach, Dietrich Klakow

* Accepted to AfricaNLP 2022 (non-archival) 

  Access Paper or Ask Questions

Call-sign recognition and understanding for noisy air-traffic transcripts using surveillance information


Apr 13, 2022
Alexander Blatt, Martin Kocour, Karel Veselý, Igor Szöke, Dietrich Klakow

* Accepted by ICASSP 2022 

  Access Paper or Ask Questions

Artefact Retrieval: Overview of NLP Models with Knowledge Base Access


Jan 24, 2022
Vilém Zouhar, Marius Mosbach, Debanjali Biswas, Dietrich Klakow

* 11 pages of main content, 7 pages of appendix; presented at AKBC CSRR 2021 

  Access Paper or Ask Questions

CLIN-X: pre-trained language models and a study on cross-task transfer for concept extraction in the clinical domain


Dec 17, 2021
Lukas Lange, Heike Adel, Jannik Strötgen, Dietrich Klakow


  Access Paper or Ask Questions

Enhancing Reinforcement Learning with discrete interfaces to learn the Dyck Language


Oct 27, 2021
Florian Dietz, Dietrich Klakow


  Access Paper or Ask Questions

Label-Descriptive Patterns and their Application to Characterizing Classification Errors


Oct 18, 2021
Michael Hedderich, Jonas Fischer, Dietrich Klakow, Jilles Vreeken


  Access Paper or Ask Questions

How Familiar Does That Sound? Cross-Lingual Representational Similarity Analysis of Acoustic Word Embeddings


Sep 21, 2021
Badr M. Abdullah, Iuliia Zaitova, Tania Avgustinova, Bernd Möbius, Dietrich Klakow

* BlackboxNLP 2021 

  Access Paper or Ask Questions

Preventing Author Profiling through Zero-Shot Multilingual Back-Translation


Sep 19, 2021
David Ifeoluwa Adelani, Miaoran Zhang, Xiaoyu Shen, Ali Davody, Thomas Kleinbauer, Dietrich Klakow

* Accepted to EMNLP 2021 (Main Conference), 9 pages 

  Access Paper or Ask Questions

Integrating Unsupervised Data Generation into Self-Supervised Neural Machine Translation for Low-Resource Languages


Jul 19, 2021
Dana Ruiter, Dietrich Klakow, Josef van Genabith, Cristina España-Bonet

* 11 pages, 8 figures, accepted at MT-Summit 2021 (Research Track) 

  Access Paper or Ask Questions

Exploring the Potential of Lexical Paraphrases for Mitigating Noise-Induced Comprehension Errors


Jul 18, 2021
Anupama Chingacham, Vera Demberg, Dietrich Klakow

* Accepted in Interspeech 2021 

  Access Paper or Ask Questions

Proceedings of the First Workshop on Weakly Supervised Learning (WeaSuL)


Jul 08, 2021
Michael A. Hedderich, Benjamin Roth, Katharina Kann, Barbara Plank, Alex Ratner, Dietrich Klakow


  Access Paper or Ask Questions

Modeling Profanity and Hate Speech in Social Media with Semantic Subspaces


Jun 18, 2021
Vanessa Hahn, Dana Ruiter, Thomas Kleinbauer, Dietrich Klakow

* 9 pages, 4 figures, accepted as a long paper at Workshop on Online Abuse and Harms 2021 

  Access Paper or Ask Questions

Do Acoustic Word Embeddings Capture Phonological Similarity? An Empirical Study


Jun 16, 2021
Badr M. Abdullah, Marius Mosbach, Iuliia Zaitova, Bernd Möbius, Dietrich Klakow

* Accepted in Interspeech 2021 

  Access Paper or Ask Questions

To Share or not to Share: Predicting Sets of Sources for Model Transfer Learning


Apr 16, 2021
Lukas Lange, Jannik Strötgen, Heike Adel, Dietrich Klakow


  Access Paper or Ask Questions

ANEA: Distant Supervision for Low-Resource Named Entity Recognition


Feb 25, 2021
Michael A. Hedderich, Lukas Lange, Dietrich Klakow


  Access Paper or Ask Questions

Emoji-Based Transfer Learning for Sentiment Tasks


Feb 12, 2021
Susann Boy, Dana Ruiter, Dietrich Klakow

* 6 pages, 2 figures, accepted at EACL-SRW 2021 

  Access Paper or Ask Questions

Analysing the Noise Model Error for Realistic Noisy Label Data


Jan 24, 2021
Michael A. Hedderich, Dawei Zhu, Dietrich Klakow

* Accepted at AAAI 2021, additional material at https://github.com/uds-lsv/noise-estimation 

  Access Paper or Ask Questions

A Closer Look at Linguistic Knowledge in Masked Language Models: The Case of Relative Clauses in American English


Nov 02, 2020
Marius Mosbach, Stefania Degaetano-Ortlieb, Marie-Pauline Krielke, Badr M. Abdullah, Dietrich Klakow

* Accepted to COLING 2020 

  Access Paper or Ask Questions

Fusion Models for Improved Visual Captioning


Oct 28, 2020
Marimuthu Kalimuthu, Aditya Mogadala, Marius Mosbach, Dietrich Klakow

* Under review at "Multi-Modal Deep Learning: Challenges and Applications", ICPR-2020 

  Access Paper or Ask Questions

A Survey on Recent Approaches for Natural Language Processing in Low-Resource Scenarios


Oct 23, 2020
Michael A. Hedderich, Lukas Lange, Heike Adel, Jannik Strötgen, Dietrich Klakow


  Access Paper or Ask Questions

Adversarial Learning of Feature-based Meta-Embeddings


Oct 23, 2020
Lukas Lange, Heike Adel, Jannik Strötgen, Dietrich Klakow


  Access Paper or Ask Questions

Rediscovering the Slavic Continuum in Representations Emerging from Neural Models of Spoken Language Identification


Oct 22, 2020
Badr M. Abdullah, Jacek Kudera, Tania Avgustinova, Bernd Möbius, Dietrich Klakow

* Accepted in VarDial 2020 Workshop 

  Access Paper or Ask Questions

Transfer Learning and Distant Supervision for Multilingual Transformer Models: A Study on African Languages


Oct 07, 2020
Michael A. Hedderich, David Adelani, Dawei Zhu, Jesujoba Alabi, Udia Markus, Dietrich Klakow

* Accepted at EMNLP'20 

  Access Paper or Ask Questions