Papers by Malte Ostendorff
CommonLID: Re-evaluating State-of-the-Art Language Identification Performance on Web Data (2026.acl-long)
Copied to clipboard
Pedro Ortiz Suarez, Laurie Burchell, Catherine Arnett, Rafael Mosquera, Sara Hincapié Monsalve, Thom Vaughan, Damian Stewart, Malte Ostendorff, Idris Abdulmumin, Vukosi Marivate, Shamsuddeen Hassan Muhammad, Atnafu Lambebo Tonja, Hend Al-Khalifa, Nadia Ghezaiel Hammouda, Verrah Akinyi Otiende, Tack Hwa Wong, Jakhongir Saydaliev, Melika Nobakhtian, Muhammad Ravi Shulthan Habibi, Chalamalasetti Kranti, Carol Muchemi, Khang Nguyen, Faisal Muhammad Adam, Luis Frentzen Salim, Reem Alqifari, Cynthia Jayne Amol, Joseph Marvin Imperial, Ilker Kesen, Ahmad Mustafid, Pavel Stepachev, Leshem Choshen, David Anugraha, Hamada Nayel, Seid Muhie Yimam, Vallerie Alexandra Putra, My Chiffon Nguyen, Azmine Toushik Wasi, Gouthami Vadithya, Rob Van Der Goot, Lanwenn ar C’horr, Karan Dua, Andrew Yates, Mithil Bangera, Yeshil Bangera, Hitesh Laxmichand Patel, Shu Okabe, Fenal Ashokbhai Ilasariya, Dmitry Gaynullin, Genta Indra Winata, Yiyuan Li, Juan Pablo Martínez, Amit Agarwal, Ikhlasul Akmal Hanif, Raia Abu Ahmad, Esther Adenuga, Filbert Aurelian Tjiaranata, Weerayut Buaphet, Michael Anugraha, Sowmya Vajjala, Benjamin L Rice, Azril Hafizi Amirudin, Jesujoba Oluwadara Alabi, Srikant Panda, Yassine Toughrai, Bruhan Kyomuhendo, Daniel Ruffinelli, null Akshata, Manuel Goulão, Ej Zhou, Ingrid Gabriela Franco Ramirez, Cristina Aggazzotti, Konstantin Dobler, Jun Kevin, Quentin Pagès, Nicholas Andrews, Nuhu Ibrahim, Mattes Ruckdeschel, Amr Keleg, Mike Zhang, Casper Rufaro Muziri, Saron Samuel, Sotaro Takeshita, Kun Kerdthaisong, Luca Foppiano, Rasul Dent, Tommaso Green, Ahmad Mustapha Wali, Kamohelo Makaaka, Vicky Feliren, Inshirah Idris, Hande Celikkanat, Abdulhamid Abubakar, Jean Maillard, Benoît Sagot, Thibault Clérice, Kenton Murray, Sarah K. K. Luger
| Challenge: | Language identification (LID) is a fundamental step in curating multilingual corpora. |
| Approach: | They introduce CommonLID, a community-driven, human-annotated LID benchmark for the web domain, covering 109 languages. |
| Outcome: | The proposed benchmark covers 109 languages and shows that existing evaluations overestimate accuracy for many languages in the web domain. |
Aspect-based Document Similarity for Research Papers (2020.coling-main)
Copied to clipboard
| Challenge: | Traditional document similarity measures do not consider in what aspects two documents are similar. |
| Approach: | They extend document similarity with aspect information by performing a pairwise document classification task. |
| Outcome: | The proposed approach is best performing on 172,073 research paper pairs from the ACL Anthology and CORD-19 corpus. |
Symmetric Dot-Product Attention for Efficient Training of BERT Language Models (2024.findings-acl)
Copied to clipboard
| Challenge: | Transformer-based models are stretched to enormous sizes, requiring increasingly larger training datasets and unsustainable amount of compute resources. |
| Approach: | They propose an alternative compatibility function for the Transformer-based attention mechanism that exploits an overlap in the learned representation of the traditional scaled dot-product attention mechanism. |
| Outcome: | The proposed model achieves 79.36 on the GLUE benchmark against 78.74 for the traditional implementation and reduces the number of trainable parameters by 6%. |
Generating Extended and Multilingual Summaries with Pre-trained Transformers (2022.lrec-1)
Copied to clipboard
| Challenge: | Almost all summarisation methods focus on a single language and short summaries. |
| Approach: | They propose a dataset for extended summarisation tailored for 11 sentences . they compare three multilingual transformer models on extractive and abstractive summarization tasks . |
| Outcome: | The proposed dataset is tailored for extended summaries of approx. 11 sentences. |
HiStruct+: Improving Extractive Text Summarization with Hierarchical Structure Information (2022.findings-acl)
Copied to clipboard
| Challenge: | Existing models that treat texts as linear sequences do not include hierarchical structure information. |
| Approach: | They propose to inject hierarchical structure information into an extractive summarization model by combining hierarchically structured text with a pre-trained Transformer language model. |
| Outcome: | The proposed model outperforms a baseline model on PubMed and arXiv datasets and the hierarchical structure information is not injected. |
Semantic Relations between Text Segments for Semantic Storytelling: Annotation Tool - Dataset - Evaluation (2022.lrec-1)
Copied to clipboard
| Challenge: | Semantic Storytelling is the goal of the future to generate stories based on extracted, processed, classified and annotated information from large content resources. |
| Approach: | They propose to create an automatic classifier for semantic relations between extracted text segments from different news articles. |
| Outcome: | The proposed method has high accuracy scores and is validated by a trained model. |
Neighborhood Contrastive Learning for Scientific Document Representations with Citation Embeddings (2022.emnlp-main)
Copied to clipboard
| Challenge: | Prior work relies on discrete citation relations to generate contrast samples, but discrete ones enforce a hard cut-off to similarity. |
| Approach: | They propose to use nearest neighbor sampling to learn continuous similarity and to sample hard-to-learn negatives and positives by controlling the sampling margin between them. |
| Outcome: | The proposed method outperforms the state-of-the-art on the SciDocs benchmark and can train (or tune) language models sample-efficiently. |
Named Entities in Medical Case Reports: Corpus and Experiments (2020.lrec-1)
Copied to clipboard
| Challenge: | Only very few annotated corpora in the medical domain exist. |
| Approach: | They propose to annotate medical entities in case reports from PubMed Central's open access library. |
| Outcome: | The proposed corpus is the first of its kind to be made available to the scientific community in English. |
Multi-LMentry: Can Multilingual LLMs Solve Elementary Tasks Across Languages? (2025.emnlp-main)
Copied to clipboard
Luca Moroni, Javier Aula-Blasco, Simone Conia, Irene Baucells, Naiara Perez, Silvia Paniagua Suárez, Anna Sallés, Malte Ostendorff, Júlia Falcão, Guijin Son, Aitor Gonzalez-Agirre, Roberto Navigli, Marta Villegas
| Challenge: | a recent study focused on complex, high-level tasks, but LMentry is limited to English . a multilingual evaluation of large language models is needed to address this gap, authors say . |
| Approach: | They propose a compact benchmark that enables systematic evaluation of large language models . they propose to use tasks that are trivial for humans but remain surprisingly difficult for LLMs . |
| Outcome: | The proposed benchmark is limited to English, leaving its insights linguistically narrow. |
Tokenizer Choice For LLM Training: Negligible or Crucial? (2024.findings-naacl)
Copied to clipboard
Mehdi Ali, Michael Fromm, Klaudia Thellmann, Richard Rutmann, Max Lübbering, Johannes Leveling, Katrin Klug, Jan Ebert, Niclas Doll, Jasper Buschhoff, Charvi Jain, Alexander Weber, Lena Jurkschat, Hammam Abdelwahab, Chelsea John, Pedro Ortiz Suarez, Malte Ostendorff, Samuel Weinbach, Rafet Sifa, Stefan Kesselheim, Nicolas Flores-Herr
| Challenge: | Recent success of large language models has been driven by curating the training dataset composition, scaling of model architectures and advancements in pretraining objectives, leaving tokenizer influence as a blind spot. |
| Approach: | They conduct a comprehensive study on the influence of tokenizer choice on LLM downstream performance by training 24 mono- and multilingual LLMs at a 2.6B parameter scale. |
| Outcome: | The proposed model can significantly impact the model's downstream performance and training costs. |
A CURATEd CATalog: Rethinking the Extraction of Pretraining Corpora for Mid-Resourced Languages (2024.lrec-main)
Copied to clipboard
Jorge Palomar-Giner, Jose Javier Saiz, Ferran Espuña, Mario Mina, Severino Da Dalt, Joan Llop, Malte Ostendorff, Pedro Ortiz Suarez, Georg Rehm, Aitor Gonzalez-Agirre, Marta Villegas
| Challenge: | CATalog 1.0 is the largest text corpus in Catalan to date . CURATE is a pipeline that can be parallelizable to run in high performance clusters . |
| Approach: | They propose a data pipeline that uses binary filters to filter documents based on text quality . they optimised the pipeline to run in high performance clusters . |
| Outcome: | The proposed pipeline is optimized for high performance cluster environments and runs in high performance. |
Claim Extraction and Law Matching for COVID-19-related Legislation (2022.lrec-1)
Copied to clipboard
| Challenge: | Existing approaches to extract legal claims from news articles and match them with applicable laws are difficult for laypersons to learn since news articles do not refer to underlying laws. |
| Approach: | They propose an automated approach to extract legal claims from news articles and match the claims with applicable laws. |
| Outcome: | The proposed model achieves 46.7 F1 for claim extraction and 91.4 F1 law matching, despite conceptual limitations. |