publications

2026

1. Does Contextual Informativeness Predict Preschoolers’ Word Learning from Stories?

   Maria Valentini, Julisa Granados, Katharina von der Wense, and Eliana Colunga

   In Proceedings of the Annual Meeting of the Cognitive Science Society, 2026
2. From If-Statements to ML Pipelines: Revisiting Bias in Code-Generation

   Minh Duc Bui, Xenia Heilmann, Mattia Cerrato, Manuel Mager, and Katharina von der Wense

   In Findings of the Association for Computational Linguistics: ACL 2026, 2026
3. Large Language Models Are Overconfident in Their Own Responses

   Mario Sanz-Guerrero, Manuel Mager, and Katharina von der Wense

   In Findings of the Association for Computational Linguistics: ACL 2026, 2026
4. Meenz bleibt Meenz, but Large Language Models Do Not Speak Its Dialect

   Minh Duc Bui, Manuel Mager, Peter Herbert Kann, and Katharina von der Wense

   In Proceedings of the Fifteenth Language Resources and Evaluation Conference (LREC 2026), 2026

2025

1. Mitigating Label Length Bias in Large Language Models

   Mario Sanz-Guerrero, and Katharina von der Wense

   In Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics, 2025
2. NALA_MAINZ at BLP-2025 Task 2: A Multi-agent Approach for Bangla Instruction to Python Code Generation

   Hossain Shaikh Saadi, Faria Alam, Mario Sanz-Guerrero, Minh Duc Bui, Manuel Mager, and Katharina von der Wense

   In Proceedings of the Workshop on Bangla Language Processing (BLP 2025), 2025
3. Dialogue Acts as a Lens on Human–LLM Interaction: Analyzing Conversational Norms in Model-Generated Responses

   Arunima Maitra, Dorothea French, and Katharina von der Wense

   In Proceedings of the Workshop on Bridging Human–Computer Interaction and Natural Language Processing (HCI+NLP 2025), 2025
4. JGU Mainz’s submission to the WMT25 shared task on LLMs with limited resources for Slavic languages: MT and QA

   Hossain Shaikh Saadi, Minh Duc Bui, Mario Sanz-Guerrero, and Katharina von der Wense

   In Proceedings of the Tenth Conference on Machine Translation (WMT 2025), 2025
5. Molecular String Representation Preferences in Pretrained LLMs: A Comparative Study in Zero- & Few-Shot Molecular Property Prediction

   George Arthur Baker, Mario Sanz-Guerrero, and Katharina von der Wense

   In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025
6. Large Language Models Discriminate Against Speakers of German Dialects

   Minh Duc Bui, Carolin Holtermann, Valentin Hofmann, Anne Lauscher, and Katharina von der Wense

   In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025
7. Interdisciplinary Research in Conversation: A Case Study in Computational Morphology for Language Documentation

   Enora Rice, Katharina von der Wense, and Alexis Palmer

   In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025
8. Mind the Gap: A Closer Look at Tokenization for Multiple-Choice Question Answering with LLMs

   Mario Sanz-Guerrero, Minh Duc Bui, and Katharina von der Wense

   In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025
9. ReSeeding Latent States for Sequential Language Understanding

   Stéphane Aroca-Ouellette, Katharina von der Wense, and Alessandro Roncone

   In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025
10. Model-Based Ranking of Source Languages for Zero-Shot Cross-Lingual Transfer

    Abteen Ebrahimi, Adam Wiemerslage, and Katharina von der Wense

    In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025
11. Linguistic Alignment Predicts Learning in Small Group Tutoring Sessions

    Dorothea French, Robert Moulder, Kelechi Ezema, Katharina von der Wense, and Sidney K. D’Mello

    In Findings of the Association for Computational Linguistics: EMNLP 2025, 2025
12. Implicitly Aligning Humans and Autonomous Agents through Shared Task Abstractions

    Stéphane Aroca-Ouellette, Miguel Aroca-Ouellette, Katharina von der Wense, and Alessandro Roncone

    In Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence (IJCAI 2025), 2025
13. On Generalization across Measurement Systems: LLMs Entail More Test-Time Compute for Underrepresented Cultures

    Minh Duc Bui, Kyung eun Park, Goran Glavaš, Fabian David Schmidt, and Katharina von der Wense

    In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics, 2025
14. Improving Low-Resource Morphological Inflection via Self-Supervised Objectives

    Adam Wiemerslage, and Katharina von der Wense

    In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics, 2025
15. Understanding the Gap: an Analysis of Research Collaborations in NLP and Language Documentation

    Luke Gessler, Alexis Palmer, and Katharina von der Wense

    In Findings of the Association for Computational Linguistics: ACL 2025, 2025
16. MALAMUTE: A Multilingual, Highly-granular, Template-free, Education-based Probing Dataset

    Sagi Shaier, George Arthur Baker, Chiranthan Sridhar, Lawrence Hunter, and Katharina von der Wense

    In Findings of the Association for Computational Linguistics: ACL 2025, 2025
17. CLIX: Cross-Lingual Explanations of Idiomatic Expressions

    Aaron Gluck, Katharina von der Wense, and Maria Leonor Pacheco

    In Findings of the Association for Computational Linguistics: ACL 2025, 2025
18. The Effectiveness of Uncased Tokenization for Clinical Notes

    Cory Paik, and Katharina von der Wense

    In Findings of the Association for Computational Linguistics: ACL 2025, 2025
19. Untangling the Influence of Typology, Data, and Model Architecture on Ranking Transfer Languages for Cross-Lingual POS Tagging

    Enora Rice, Ali Marashian, Hannah Haynie, Katharina von der Wense, and Alexis Palmer

    In Proceedings of the Workshop on Language Models for Underserved Communities (LM4UC 2025), 2025
20. Corrective In-Context Learning: Evaluating Self-Correction in Large Language Models

    Mario Sanz-Guerrero, and Katharina von der Wense

    In Proceedings of the Workshop on Insights from Negative Results in NLP, 2025
21. Findings of the AmericasNLP 2025 Shared Tasks on Machine Translation, Creation of Educational Material, and Translation Metrics for Indigenous Languages of the Americas

    Ona De Gibert, Robert Pugh, Ali Marashian, Raul Vazquez, Abteen Ebrahimi, Pavel Denisov, Enora Rice, Edward Gow-Smith, Juan Prieto, Melissa Robles, Rubén Manrique, Oscar Moreno, Angel Lino, Rolando Coto-Solano, Aldo Alvarez, Marvin Agüero-Torales, John E. Ortega, Luis Chiruzzo, Arturo Oncevay, Shruti Rijhwani, Katharina von der Wense, and Manuel Mager

    In Proceedings of the Fifth Workshop on NLP for Indigenous Languages of the Americas (AmericasNLP), 2025
22. Multi3Hate: Multimodal, Multilingual, and Multicultural Hate Speech Detection with Vision–Language Models

    Minh Duc Bui, Katharina von der Wense, and Anne Lauscher

    In Proceedings of the 2025 Conference of the North American Chapter of the Association for Computational Linguistics, 2025
23. More Experts Than Galaxies: Conditionally-Overlapping Experts with Biologically-Inspired Fixed Routing

    Sagi Shaier, Francisco Pereira, Katharina von der Wense, Lawrence Hunter, and Matt Jones

    In The Thirteenth International Conference on Learning Representations (ICLR 2025), 2025
24. Asking Again and Again: Exploring LLM Robustness to Repeated Questions

    Sagi Shaier, Mario Sanz-Guerrero, and Katharina von der Wense

    2025
25. From Priest to Doctor: Domain Adaptation for Low-Resource Neural Machine Translation

    Ali Marashian, Enora Rice, Luke Gessler, Alexis Palmer, and Katharina von der Wense

    In Proceedings of the 31st International Conference on Computational Linguistics, 2025
26. Measuring Contextual Informativeness in Child-Directed Text

    Maria R. Valentini, Téa Y. Wright, Ali Marashian, Jennifer M. Ellis, Eliana Colunga, and Katharina von der Wense

    In Proceedings of the 31st International Conference on Computational Linguistics, 2025

2024

1. Identifying Telescope Usage in Astrophysics Publications: A Machine Learning Framework for Institutional Research Management at Observatories

   Vicente Amado Olivo, Wolfgang Kerzendorf, Brian Cherinka, Joshua V. Shields, Annie Didier, and Katharina von der Wense

   The Astronomical Journal 2024
2. Getting The Most Out of Your Training Data: Exploring Unsupervised Tasks for Morphological Inflection

   Abhishek Purushothama, Adam Wiemerslage, and Katharina von der Wense

   In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 2024
3. It Is Not About What You Say, It Is About How You Say It: A Surprisingly Simple Approach for Improving Reading Comprehension

   Sagi Shaier, Lawrence Hunter, and Katharina von der Wense

   In Findings of the Association for Computational Linguistics ACL 2024, 2024
4. TAMS: Translation-Assisted Morphological Segmentation

   Enora Rice, Ali Marashian, Luke Gessler, Alexis Palmer, and Katharina von der Wense

   In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2024
5. Aligning to Adults Is Easy, Aligning to Children Is Hard: A Study of Linguistic Alignment in Dialogue Systems

   Dorothea French, Sidney D’Mello, and Katharina von der Wense

   In Proceedings of the 1st Human-Centered Large Language Modeling Workshop, 2024
6. Eyes on the Game: Deciphering Implicit Human Signals to Infer Human Proficiency, Trust, and Intent

   Nikhil Hulle, Stephane Aroca-Ouellette, Anthony Ries, Jake Brawer, Katharina von der Wense, and Alessandro Roncone

   In Proceedings of the 2024 33rd IEEE International Conference on Robot and Human Interactive Communication (ROMAN), 2024
7. Findings of the AmericasNLP 2024 Shared Task on Machine Translation into Indigenous Languages

   Abteen Ebrahimi, Ona Gibert, Raul Vazquez, Rolando Coto-Solano, Pavel Denisov, Robert Pugh, Manuel Mager, Arturo Oncevay, Luis Chiruzzo, Katharina von der Wense, and Shruti Rijhwani

   In Proceedings of the 4th Workshop on Natural Language Processing for Indigenous Languages of the Americas (AmericasNLP 2024), 2024
8. Findings of the AmericasNLP 2024 Shared Task on the Creation of Educational Materials for Indigenous Languages

   Luis Chiruzzo, Pavel Denisov, Alejandro Molina-Villegas, Silvia Fernandez-Sabido, Rolando Coto-Solano, Marvin Agüero-Torales, Aldo Alvarez, Samuel Canul-Yah, Lorena Hau-Ucán, Abteen Ebrahimi, Robert Pugh, Arturo Oncevay, Shruti Rijhwani, Katharina von der Wense, and Manuel Mager

   In Proceedings of the 4th Workshop on Natural Language Processing for Indigenous Languages of the Americas (AmericasNLP 2024), 2024
9. Evaluating LLMs as Tools to Support Early Vocabulary Learning

   Jennifer Weber, Maria Valentini, Téa Wright, Katharina von der Wense, and Eliana Colunga

   In Proceedings of the Annual Meeting of the Cognitive Science Society, 2024
10. Prompting as Panacea? A Case Study of In-Context Learning Performance for Qualitative Coding of Classroom Dialog

    Ananya Ganesh, Chelsea Chandler, Sidney D’Mello, Martha Palmer, and Katharina von der Wense

    In Proceedings of the International Conference on Educational Data Mining, 2024
11. Zero-Shot vs. Translation-Based Cross-Lingual Transfer: The Case of Lexical Gaps

    Abteen Ebrahimi, and Katharina von der Wense

    In Proceedings of the 2024 Annual Conference of the North American Chapter of the Association for Computational Linguistics, 2024
12. Knowledge Distillation vs. Pretraining from Scratch under a Fixed (Computation) Budget

    Minh Duc Bui, Fabian David Schmidt, Goran Glavaš, and Katharina von der Wense

    In Proceedings of the Workshop on Insights from Negative Results in NLP, 2024
13. The Trade-off between Performance, Efficiency, and Fairness in Adapter Modules for Text Classification

    Minh Duc Bui, and Katharina von der Wense

    In Proceedings of the Fourth Workshop on Trustworthy Natural Language Processing, 2024
14. NLP for Language Documentation: Two Reasons for the Gap between Theory and Practice

    Luke Gessler, and Katharina von der Wense

    In Proceedings of the 4th Workshop on Natural Language Processing for Indigenous Languages of the Americas (AmericasNLP), 2024
15. JGU Mainz’s Submission to the AmericasNLP 2024 Shared Task on the Creation of Educational Materials for Indigenous Languages

    Minh Duc Bui, and Katharina von der Wense

    In Proceedings of the 4th Workshop on Natural Language Processing for Indigenous Languages of the Americas (AmericasNLP), 2024
16. Quantifying the Hyperparameter Sensitivity of Neural Networks for Character-level Sequence-to-Sequence Tasks

    Adam Wiemerslage, Kyle Gorman, and Katharina von der Wense

    In Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics, 2024
17. Comparing Template-based and Template-free Language Model Probing

    Sagi Shaier, Kevin Bennett, Lawrence Hunter, and Katharina von der Wense

    In Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics, 2024
18. Desiderata For The Context Use Of Question Answering Systems

    Sagi Shaier, Lawrence Hunter, and Katharina von der Wense

    In Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics, 2024

2023

1. On the Automatic Generation and Simplification of Children’s Stories

   Maria Valentini, Jennifer Weber, Jesus Salcido, Téa Wright, Eliana Colunga, and Katharina von der Wense

   In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, 2023
2. Emerging Challenges in Personalized Medicine: Assessing Demographic Effects on Biomedical Question Answering Systems

   Sagi Shaier, Kevin Bennett, Lawrence Hunter, and Katharina von der Wense

   In Proceedings of the 13th International Joint Conference on Natural Language Processing and the 3rd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics, 2023
3. Who Are All The Stochastic Parrots Imitating? They Should Tell Us!

   Sagi Shaier, Lawrence Hunter, and Katharina von der Wense

   In Proceedings of the 13th International Joint Conference on Natural Language Processing and the 3rd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics, 2023
4. Findings of the CoCo4MT 2023 Shared Task on Corpus Construction for Machine Translation

   Ananya Ganesh, Marine Carpuat, William Chen, Katharina Kann, Constantine Lignos, John E. Ortega, Jonne Saleva, Shabnam Tafreshi, and Rodolfo Zevallos

   In Proceedings of the Second Workshop on Corpus Generation and Corpus Augmentation for Machine Translation, 2023
5. Neural Machine Translation for the Indigenous Languages of the Americas: An Introduction

   Manuel Mager, Rajat Bhatnagar, Graham Neubig, Ngoc Thang Vu, and Katharina Kann

   In Proceedings of the Third Workshop on NLP for Indigenous Languages of the Americas, 2023
6. Findings of the AmericasNLP 2023 Shared Task on Machine Translation into Indigenous Languages

   Abteen Ebrahimi, Manuel Mager, Shruti Rijhwani, Enora Rice, Arturo Oncevay, Claudia Baltazar, María Cortés, Cynthia Montaño, John E Ortega, Rolando Coto-Solano, Hilaria Cruz, Alexis Palmer, and Katharina Kann

   In Proceedings of the Third Workshop on NLP for Indigenous Languages of the Americas, 2023
7. A Survey of Challenges and Methods in the Computational Modeling of Multi-Party Dialog

   Ananya Ganesh, Martha Palmer, and Katharina Kann

   In Proceedings of the 5th Workshop on NLP for Conversational AI, 2023
8. Mind the Gap between the Application Track and the Real World

   Ananya Ganesh, Jie Cao, Margaret Perkoff, Rosy Southwell, Martha Palmer, and Katharina Kann

   In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics, 2023
9. Ethical Considerations for Machine Translation of Indigenous Languages: Giving a Voice to the Speakers

   Manuel Mager, Elisabeth Albine Mager, Katharina Kann, and Ngoc Thang Vu

   In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics, 2023
10. An Investigation of Noise in Morphological Inflection

    Adam Wiemerslage, Changbing Yang, Garrett Nicolai, Miikka Silfverberg, and Katharina Kann

    In Findings of the 61st Annual Meeting of the Association for Computational Linguistics, 2023
11. A Comparative Analysis of Automatic Speech Recognition Errors in Small Group Classroom Discourse

    Jie Cao, Ananya Ganesh, Jon Cai, Rosy Southwell, Margaret Perkoff, Michael Reagan, Katharina Kann, James Martin, Martha Palmer, and Sidney D’Mello

    In Proceedings of the 31st ACM Conference on User Modeling, Adaptation and Personalization, 2023
12. Navigating Wanderland: Highlighting Off-Task Discussions in Classrooms

    Ananya Ganesh, Michael Chang, Rachel Dickler, Michael Regan, Jon Cai, Kristin Wright-Bettner, James Pustejovsky, James Martin, Jeff Flanigan, Martha Palmer, and Katharina Kann

    In Proceedings of the 24th International Conference on Artificial Intelligence in Education, 2023
13. Meeting the Needs of Low-Resource Languages: Exploring Automatic Alignments via Pretrained Models

    Abteen Ebrahimi, Arya D. McCarthy, Arturo Oncevay, John E. Ortega, Luis Chiruzzo, Rolando Coto-Solano, Gustavo A. Giménez-Lugo, and Katharina Kann

    In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, 2023

2022

1. Findings of the Second AmericasNLP Competition on Speech-to-Text Translation

   Abteen Ebrahimi, Manuel Mager, Adam Wiemerslage, Pavel Denisov, Arturo Oncevay, Danni Liu, Sai Koneru, Enes Yavuz Ugan, Zhaolin Li, Jan Niehues, Monica Romero, Ivan G Torre, Tanel Alumäe, Jiaming Kong, Sergey Polezhaev, Yury Belousov, Wei-Rui Chen, Peter Sullivan, Ife Adebara, Bashar Talafha, Alcides Alcoba Inciarte, Muhammad Abdul-Mageed, Luis Chiruzzo, Rolando Coto-Solano, Hilaria Cruz, Sofía Flores-Solórzano, Aldo Andrés Alvarez López, Ivan Meza-Ruiz, John E. Ortega, Alexis Palmer, Rodolfo Joel Zevallos Salazar, Kristine Stenzel, Thang Vu, and Katharina Kann

   In Proceedings of the NeurIPS 2022 Competitions Track, 2022

   Abs PDF

   Indigenous languages, including those from the Americas, have received very little attention from the machine learning (ML) and natural language processing (NLP) communities. To tackle the resulting lack of systems for these languages and the accompanying social inequalities affecting their speakers, we conduct the second AmericasNLP competition (and the first one in collaboration with NeurIPS), which is centered around speech-to-text translation systems for Indigenous languages of the Americas. The competition features three tasks – (1) automatic speech recognition, (2) text-based machine translation, and (3) speech-to-text translation – and two tracks: constrained and unconstrained. Five Indigenous languages are covered: Bribri, Guarani, Kotiria, Wa’ikhana, and Quechua. In this overview paper, we describe the tasks, tracks, and languages, introduce the baseline and participating systems, and end with a summary of ongoing and future challenges for the automatic translation of Indigenous languages.

2. AmericasNLI: Machine translation and natural language inference systems for Indigenous languages of the Americas

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

   Frontiers in Artificial Intelligence 2022

   Abs

   Little attention has been paid to the development of human language technology for truly low-resource languages—i.e., languages with limited amounts of digitally available text data, such as Indigenous languages. However, it has been shown that pretrained multilingual models are able to perform crosslingual transfer in a zero-shot setting even for low-resource languages which are unseen during pretraining. Yet, prior work evaluating performance on unseen languages has largely been limited to shallow token-level tasks. It remains unclear if zero-shot learning of deeper semantic tasks is possible for unseen languages. To explore this question, we present AmericasNLI, a natural language inference dataset covering 10 Indigenous languages of the Americas. We conduct experiments with pretrained models, exploring zero-shot learning in combination with model adaptation. Furthermore, as AmericasNLI is a multiway parallel dataset, we use it to benchmark the performance of different machine translation models for those languages. Finally, using a standard transformer model, we explore translation-based approaches for natural language inference. We find that the zero-shot performance of pretrained models without adaptation is poor for all languages in AmericasNLI, but model adaptation via continued pretraining results in improvements. All machine translation models are rather weak, but, surprisingly, translation-based approaches to natural language inference outperform all other models on that task.

3. A Major Obstacle for NLP Research: Let’s Talk about Time Allocation!

   Katharina Kann, Shiran Dudy, and Arya D. McCarthy

   In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, 2022
4. A Comprehensive Comparison of Neural Networks as Cognitive Models of Inflection

   Adam Wiemerslage, Shiran Dudy, and Katharina Kann

   In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, 2022
5. CHIA: CHoosing Instances to Annotate for Machine Translation

   Rajat Bhatnagar, Ananya Ganesh, and Katharina Kann

   In Findings of the 2022 Conference on Empirical Methods in Natural Language Processing, 2022
6. Generate Me a Bedtime Story: Leveraging Natural Language Processing for Early Vocabulary Enhancement

   Trevor A. Hall, Maria Valentini, Eliana Colunga, and Katharina Kann

   In Proceedings of the Workshop on NLP for Positive Impact, 2022
7. Machine Translation Between High-resource Languages in a Language Documentation Setting

   Katharina Kann, Abteen Ebrahimi, Kristine Stenzel, and Alexis Palmer

   In Proceedings of the First Workshop on Applying NLP to Field Linguistics, 2022
8. Response Construct Tagging: NLP-Aided Assessment for Engineering Education

   Ananya Ganesh, Hugh Scribner, Jasdeep Singh, Katherine Goodman, Jean Hertzberg, and Katharina Kann

   In Proceedings of the 17th Workshop on Innovative Use of NLP for Building Educational Applications, 2022
9. Open-domain Dialogue Generation: What We Can Do, Cannot Do, And Should Do Next

   Katharina Kann, Abteen Ebrahimi, Joewie J. Koh, Shiran Dudy, and Alessandro Roncone

   In Proceedings of the 4th Workshop on NLP for Conversational AI, 2022

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

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

    In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics, 2022

    Video
11. How Does Multilingual Pretraining Affect Cross-Lingual Transferability?

    Yoshinari Fujinuma, Jordan Lee Boyd-Graber, and Katharina Kann

    In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics, 2022
12. Morphological Processing of Low-Resource Languages: Where We Are and What’s Next

    Adam Wiemerslage, Miikka Silfverberg, Changbing Yang, Arya D. McCarthy, Garrett Nicolai, Eliana Colunga, and Katharina Kann

    In Findings of the 60th Annual Meeting of the Association for Computational Linguistics, 2022

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

    Manuel Mager, Arturo Oncevay, Elisabeth Mager, Katharina Kann, and Thang Vu

    In Findings of the 60th Annual Meeting of the Association for Computational Linguistics, 2022

2021

1. The World of an Octopus: How Reporting Bias Influences a Language Model’s Perception of Color

   Cory Paik, Stéphane Aroca-Ouellette, Alessandro Roncone, and Katharina Kann

   In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, 2021

   Abs

   Recent work has raised concerns about the inherent limitations of text-only pretraining. In this paper, we first demonstrate that reporting bias, the tendency of people to not state the obvious, is one of the causes of this limitation, and then investigate to what extent multimodal training can mitigate this issue. To accomplish this, we 1) generate the Color Dataset (CoDa), a dataset of human-perceived color distributions for 521 common objects; 2) use CoDa to analyze and compare the color distribution found in text, the distribution captured by language models, and a human’s perception of color; and 3) investigate the performance differences between text-only and multimodal models on CoDa. Our results show that the distribution of colors that a language model recovers correlates more strongly with the inaccurate distribution found in text than with the ground-truth, supporting the claim that reporting bias negatively impacts and inherently limits text-only training. We then demonstrate that multimodal models can leverage their visual training to mitigate these effects, providing a promising avenue for future research.

2. What Would a Teacher Do? Predicting Future Talk Moves

   Ananya Ganesh, Martha Palmer, and Katharina Kann

   In Findings of the 59th Annual Meeting of the Association for Computational Linguistics, 2021
3. PROST: Physical Reasoning of Objects through Space and Time

   Stephane Aroca-Ouellette, Cory Paik, Alessandro Roncone, and Katharina Kann

   In Findings of the 59th Annual Meeting of the Association for Computational Linguistics, 2021
4. How to Adapt Your Pretrained Multilingual Model to 1600 Languages

   Abteen Ebrahimi, and Katharina Kann

   In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics, 2021
5. Don’t Rule Out Monolingual Speakers: A Method For Crowdsourcing Machine Translation Data

   Rajat Bhatnagar, Ananya Ganesh, and Katharina Kann

   In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics, 2021
6. Findings of the LoResMT 2021 Shared Task on COVID and Sign Language for Low-resource Languages

   Atul Kr. Ojha, Chao-Hong Liu, Katharina Kann, John Ortega, Sheetal Shatam, and Theodorus Fransen

   In Proceedings of the 4th Workshop on Technologies for MT of Low Resource Languages (LoResMT2021), 2021

   Abs

   We present the findings of the LoResMT 2021 shared task which focuses on machine translation (MT) of COVID-19 data for both low-resource spoken and sign languages. The organization of this task was conducted as part of the fourth workshop on technologies for machine translation of low resource languages (LoResMT). Parallel corpora is presented and publicly available which includes the following directions: English↔Irish, English↔Marathi, and Taiwanese Sign language↔Traditional Chinese. Training data consists of 8112, 20933 and 128608 segments, respectively. There are additional monolingual data sets for Marathi and English that consist of 21901 segments. The results presented here are based on entries from a total of eight teams. Three teams submitted systems for English↔Irish while five teams submitted systems for English↔Marathi. Unfortunately, there were no systems submissions for the Taiwanese Sign language↔Traditional Chinese task. Maximum system performance was computed using BLEU and follow as 36.0 for English–Irish, 34.6 for Irish–English, 24.2 for English–Marathi, and 31.3 for Marathi–English.

7. Paradigm Clustering with Weighted Edit Distance

   Andrew Gerlach, Adam Wiemerslage, and Katharina Kann

   In Proceedings of the 18th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology, 2021

   Abs

   This paper describes our system for the SIGMORPHON 2021 Shared Task on Unsupervised Morphological Paradigm Clustering, which asks participants to group inflected forms together according their underlying lemma without the aid of annotated training data. We employ agglomerative clustering to group word forms together using a metric that combines an orthographic distance and a semantic distance from word embeddings. We experiment with two variations of an edit distance-based model for quantifying orthographic distance, but, due to time constraints, our system does not improve over the shared task’s baseline system.

8. Findings of the SIGMORPHON 2021 Shared Task on Unsupervised Morphological Paradigm Clustering

   Adam Wiemerslage, Arya D. McCarthy, Alexander Erdmann, Garrett Nicolai, Manex Agirrezabal, Miikka Silfverberg, Mans Hulden, and Katharina Kann

   In Proceedings of the 18th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology, 2021

   Abs

   We describe the second SIGMORPHON shared task on unsupervised morphology: the goal of the SIGMORPHON 2021 Shared Task on Unsupervised Morphological Paradigm Clustering is to cluster word types from a raw text corpus into paradigms. To this end, we release corpora for 5 development and 9 test languages, as well as gold partial paradigms for evaluation. We receive 14 submissions from 4 teams that follow different strategies, and the best performing system is based on adaptor grammars. Results vary significantly across languages. However, all systems are outperformed by a supervised lemmatizer, implying that there is still room for improvement.

9. Findings of the AmericasNLP 2021 Shared Task on Open Machine Translation for Indigenous Languages of the Americas

   Manuel Mager, Arturo Oncevay, Abteen Ebrahimi, John Ortega, Annette Rios, Angela Fan, Ximena Gutierrez-Vasques, Luis Chiruzzo, Gustavo Giménez-Lugo, Ricardo Ramos, Ivan Vladimir Meza Ruiz, Rolando Coto-Solano, Alexis Palmer, Elisabeth Mager-Hois, Vishrav Chaudhary, Graham Neubig, Ngoc Thang Vu, and Katharina Kann

   In Proceedings of the First Workshop on Natural Language Processing for Indigenous Languages of the Americas, 2021
10. Coloring the Black Box: What Synesthesia Tells Us about Character Embeddings

    Katharina Kann, and Mauro M. Monsalve-Mercado

    In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics, 2021
11. CLiMP: A Benchmark for Chinese Language Model Evaluation

    Beilei Xiang, Changbing Yang, Yu Li, Alex Warstadt, and Katharina Kann

    In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics, 2021

2020

1. Making a Point: Pointer-Generator Transformers for Disjoint Vocabularies

   Nikhil Prabhu, and Katharina Kann

   In Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 9th International Joint Conference on Natural Language Processing Student Research Workshop, 2020

   Best Paper Award
2. English Intermediate-Task Training Improves Zero-Shot Cross-Lingual Transfer Too

   Jason Phang, Phu Mon Htut, Yada Pruksachatkun, Haokun Liu, Clara Vania, Iacer Calixto, Katharina Kann, and Samuel R. Bowman

   In Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 9th International Joint Conference on Natural Language Processing, 2020
3. Tackling the Low-resource Challenge for Canonical Segmentation

   Manuel Mager, Özlem Çetinoğlu, and Katharina Kann

   In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, 2020
4. Acrostic Poem Generation

   Rajat Agarwal, and Katharina Kann

   In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, 2020
5. IGT2P: From Interlinear Glossed Texts to Paradigms

   Sarah Moeller, Ling Liu, Changbing Yang, Katharina Kann, and Mans Hulden

   In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, 2020
6. Why Overfitting Isn’t Always Bad: Retrofitting Cross-Lingual Word Embeddings to Dictionaries

   Mozhi Zhang, Yoshinari Fujinuma, Michael J. Paul, and Jordan Boyd-Graber

   In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, 2020

   Abs

   Cross-lingual word embeddings (CLWE) are often evaluated on bilingual lexicon induction (BLI). Recent CLWE methods use linear projections, which underfit the training dictionary, to generalize on BLI. However, underfitting can hinder generalization to other downstream tasks that rely on words from the training dictionary. We address this limitation by retrofitting CLWE to the training dictionary, which pulls training translation pairs closer in the embedding space and overfits the training dictionary. This simple post-processing step often improves accuracy on two downstream tasks, despite lowering BLI test accuracy. We also retrofit to both the training dictionary and a synthetic dictionary induced from CLWE, which sometimes generalizes even better on downstream tasks. Our results confirm the importance of fully exploiting training dictionary in downstream tasks and explains why BLI is a flawed CLWE evaluation.

7. The SIGMORPHON 2020 Shared Task on Unsupervised Morphological Paradigm Completion

   Katharina Kann, Arya D. McCarthy, Garrett Nicolai, and Mans Hulden

   In Proceedings of the 17th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology, 2020

   Abs

   In this paper, we describe the findings of the SIGMORPHON 2020 shared task on unsupervised morphological paradigm completion (SIGMORPHON 2020 Task 2), a novel task in the field of inflectional morphology. Participants were asked to submit systems which take raw text and a list of lemmas as input, and output all inflected forms, i.e., the entire morphological paradigm, of each lemma. In order to simulate a realistic use case, we first released data for 5 development languages. However, systems were officially evaluated on 9 surprise languages, which were only revealed a few days before the submission deadline. We provided a modular baseline system, which is a pipeline of 4 components. 3 teams submitted a total of 7 systems, but, surprisingly, none of the submitted systems was able to improve over the baseline on average over all 9 test languages. Only on 3 languages did a submitted system obtain the best results. This shows that unsupervised morphological paradigm completion is still largely unsolved. We present an analysis here, so that this shared task will ground further research on the topic.

8. Frustratingly Easy Multilingual Grapheme-to-Phoneme Conversion

   Nikhil Prabhu, and Katharina Kann

   In Proceedings of the 17th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology, 2020

   Abs

   In this paper, we describe two CU-Boulder submissions to the SIGMORPHON 2020 Task 1 on multilingual grapheme-to-phoneme conversion (G2P). Inspired by the high performance of a standard transformer model (Vaswani et al., 2017) on the task, we improve over this approach by adding two modifications: (i) Instead of training exclusively on G2P, we additionally create examples for the opposite direction, phoneme-to-grapheme conversion (P2G). We then perform multi-task training on both tasks. (ii) We produce ensembles of our models via majority voting. Our approaches, though being conceptually simple, result in systems that place 6th and 8th amongst 23 submitted systems, and obtain the best results out of all systems on Lithuanian and Modern Greek, respectively.

9. The NYU-CUBoulder Systems for SIGMORPHON 2020 Task 0 and Task 2

   Assaf Singer, and Katharina Kann

   In Proceedings of the 17th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology, 2020

   Abs

   We describe the NYU-CUBoulder systems for the SIGMORPHON 2020 Task 0 on typologically diverse morphological inflection and Task 2 on unsupervised morphological paradigm completion. The former consists of generating morphological inflections from a lemma and a set of morphosyntactic features describing the target form. The latter requires generating entire paradigms for a set of given lemmas from raw text alone. We model morphological inflection as a sequence-to-sequence problem, where the input is the sequence of the lemma’s characters with morphological tags, and the output is the sequence of the inflected form’s characters. First, we apply a transformer model to the task. Second, as inflected forms share most characters with the lemma, we further propose a pointer-generator transformer model to allow easy copying of input characters.

10. The IMS–CUBoulder System for the SIGMORPHON 2020 Shared Task on Unsupervised Morphological Paradigm Completion

    Manuel Mager, and Katharina Kann

    In Proceedings of the 17th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology, 2020

    Abs

    In this paper, we present the systems of the University of Stuttgart IMS and the University of Colorado Boulder (IMS–CUBoulder) for SIGMORPHON 2020 Task 2 on unsupervised morphological paradigm completion (Kann et al., 2020). The task consists of generating the morphological paradigms of a set of lemmas, given only the lemmas themselves and unlabeled text. Our proposed system is a modified version of the baseline introduced together with the task. In particular, we experiment with substituting the inflection generation component with an LSTM sequence-to-sequence model and an LSTM pointer-generator network. Our pointer-generator system obtains the best score of all seven submitted systems on average over all languages, and outperforms the official baseline, which was best overall, on Bulgarian and Kannada.

11. Self-Training for Unsupervised Parsing with PRPN

    Anhad Mohananey, Katharina Kann, and Samuel R. Bowman

    In Proceedings of the 16th International Conference on Parsing Technologies and the IWPT 2020 Shared Task on Parsing into Enhanced Universal Dependencies, 2020

    Abs

    Neural unsupervised parsing (UP) models learn to parse without access to syntactic annotations, while being optimized for another task like language modeling. In this work, we propose self-training for neural UP models: we leverage aggregated annotations predicted by copies of our model as supervision for future copies. To be able to use our model’s predictions during training, we extend a recent neural UP architecture, the PRPN (Shen et al., 2018a), such that it can be trained in a semi-supervised fashion. We then add examples with parses predicted by our model to our unlabeled UP training data. Our self-trained model outperforms the PRPN by 8.1% F1 and the previous state of the art by 1.6% F1. In addition, we show that our architecture can also be helpful for semi-supervised parsing in ultra-low-resource settings.

12. Intermediate-Task Transfer Learning with Pretrained Language Models: When and Why Does It Work?

    Yada Pruksachatkun, Jason Phang, Haokun Liu, Phu Mon Htut, Xiaoyi Zhang, Richard Yuanzhe Pang, Clara Vania, Katharina Kann, and Samuel R. Bowman

    In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, 2020

    Abs

    While pretrained models such as BERT have shown large gains across natural language understanding tasks, their performance can be improved by further training the model on a data-rich intermediate task, before fine-tuning it on a target task. However, it is still poorly understood when and why intermediate-task training is beneficial for a given target task. To investigate this, we perform a large-scale study on the pretrained RoBERTa model with 110 intermediate-target task combinations. We further evaluate all trained models with 25 probing tasks meant to reveal the specific skills that drive transfer. We observe that intermediate tasks requiring high-level inference and reasoning abilities tend to work best. We also observe that target task performance is strongly correlated with higher-level abilities such as coreference resolution. However, we fail to observe more granular correlations between probing and target task performance, highlighting the need for further work on broad-coverage probing benchmarks. We also observe evidence that the forgetting of knowledge learned during pretraining may limit our analysis, highlighting the need for further work on transfer learning methods in these settings.

13. Unsupervised Morphological Paradigm Completion

    Huiming Jin, Liwei Cai, Yihui Peng, Chen Xia, Arya McCarthy, and Katharina Kann

    In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, 2020

    Abs

    We propose the task of unsupervised morphological paradigm completion. Given only raw text and a lemma list, the task consists of generating the morphological paradigms, i.e., all inflected forms, of the lemmas. From a natural language processing (NLP) perspective, this is a challenging unsupervised task, and high-performing systems have the potential to improve tools for low-resource languages or to assist linguistic annotators. From a cognitive science perspective, this can shed light on how children acquire morphological knowledge. We further introduce a system for the task, which generates morphological paradigms via the following steps: (i) EDIT TREE retrieval, (ii) additional lemma retrieval, (iii) paradigm size discovery, and (iv) inflection generation. We perform an evaluation on 14 typologically diverse languages. Our system outperforms trivial baselines with ease and, for some languages, even obtains a higher accuracy than minimally supervised systems.

14. Learning to Learn Morphological Inflection for Resource-Poor Languages

    Katharina Kann, Samuel R. Bowman, and Kyunghyun Cho

    In Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence, 2020
15. Weakly Supervised POS Taggers Perform Poorly on Truly Low-Resource Languages

    Katharina Kann, Ophélie Lacroix, and Anders Søgaard

    In Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence, 2020
16. Acquisition of Inflectional Morphology in Artificial Neural Networks With Prior Knowledge

    Katharina Kann

    In Proceedings of the Society for Computation in Linguistics, 2020