Focus

I am a Sr. Applied Scientist at Amazon in Berlin. I'm interested in efficiency in NLP and search, and in system evaluation. Currently, I serve as an area chair for the Efficient NLP track at EMNLP 2023, having also held this role in the previous years (EMNLP 2022 and 2021). Furthermore, I am co-organizing the Eval4NLP 2023 workshop on evaluation and comparison of NLP systems. I am a member of the ACL working group on Efficient NLP. In the past, I co-organized the SustaiNLP 2022 workshop on simple and efficient NLP. Before joining Amazon, I completed my PhD at UKP Lab, TU Darmstadt, where I was also a member of the senior staff. Between 2008 and 2017, I worked as a freelance software developer for direct clients and advertising firms such as SYZYGY, Ogilvy, and ETECTURE.

Publications

2023
Ji-Ung Lee, Haritz Puerto, Betty van Aken, Yuki Arase, Jessica Zosa Forde, Leon Derczynski, Andreas Rücklé, Iryna Gurevych, Roy Schwartz, Emma Strubell, and Jesse Dodge: "Surveying (Dis) Parities and Concerns of Compute Hungry NLP Research", ArXiv 2023.
Paper
2022
Yuki Arase, Phil Blunsom, Mona Diab, Jesse Dodge, Iryna Gurevych, Percy Liang, Colin Raffel, Andreas Rücklé, Roy Schwartz, Noah A. Smith, Emma Strubell, and Yue Zhang: "Efficient NLP Policy Document".
Paper
2021
Andreas Rücklé, Gregor Geigle, Max Glockner, Tilman Beck, Jonas Pfeiffer, Nils Reimers, and Iryna Gurevych: "AdapterDrop: On the Efficiency of Adapters in Transformers", EMNLP 2021.
Paper Code
Clifton Poth, Jonas Pfeiffer, Andreas Rücklé, and Iryna Gurevych: "What to Pre-Train on? Efficient Intermediate Task Selection", EMNLP 2021.
Paper Code
Nandan Thakur, Nils Reimers, Andreas Rücklé, Abhishek Srivastava, and Iryna Gurevych: "BEIR: Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models", NeurIPS 2021: Datasets and Benchmarks.
Paper Code
Nafise Sadat Moosavi, Andreas Rücklé, Dan Roth, and Iryna Gurevych: "Learning to Reason for Text Generation from Scientific Tables", NeurIPS 2021: Datasets and Benchmarks.
Paper Code
Gregor Geigle, Nils Reimers, Andreas Rücklé, and Iryna Gurevych: "TWEAC: Transformer with Extendable QA Agent Classifiers", ArXiv 2021.
Paper Code
Jonas Pfeiffer, Aishwarya Kamath, Andreas Rücklé, Kyunghyun Cho, and Iryna Gurevych: "AdapterFusion: Non-Destructive Task Composition for Transfer Learning", EACL 2021.
Paper Code
2020
Andreas Rücklé, Jonas Pfeiffer, and Iryna Gurevych: "MultiCQA: Zero-Shot Transfer of Self-Supervised Text Matching Models on a Massive Scale", EMNLP 2020.
Paper Code
Jonas Pfeiffer, Andreas Rücklé, Clifton Poth, Aishwarya Kamath, Ivan Vulić, Sebastian Ruder, Kyunghyun Cho, and Iryna Gurevych: "AdapterHub: A Framework for Adapting Transformers", EMNLP 2020 (Demo).
Paper Code
Mingzhu Wu, Nafise Sadat Moosavi, Andreas Rücklé, and Iryna Gurevych: "Improving QA Generalization by Concurrent Modeling of Multiple Biases", EMNLP-Findings 2020.
Paper Code
2019
Andreas Rücklé, Nafise Sadat Moosavi, and Iryna Gurevych: "Neural Duplicate Question Detection without Labeled Training Data", EMNLP 2019.
Paper Code
Nafise Sadat Moosavi, Prasetya Ajie Utama, Andreas Rücklé, and Iryna Gurevych: "Improving Generalization by Incorporating Coverage in Natural Language Inference", ArXiv 2019.
Paper
Steffen Eger, Andreas Rücklé, and Iryna Gurevych: "Pitfalls in the Evaluation of Sentence Embeddings", RepL4NLP 2019.
Paper
Steffen Eger, Gözde Gül Şahin, Andreas Rücklé, Ji-Ung Lee, Claudia Schulz, Mohsen Mesgar, Krishnkant Swarnkar, Edwin Simpson, and Iryna Gurevych: "Text Processing Like Humans Do: Visually Attacking and Shielding NLP Systems", NAACL 2019.
Paper Code
Andreas Rücklé, Krishnkant Swarnkar, and Iryna Gurevych: "Improved Cross-Lingual Question Retrieval for Community Question Answering", WWW 2019.
Paper Code
Andreas Rücklé, Nafise Sadat Moosavi, and Iryna Gurevych: "COALA: A Neural Coverage-Based Approach for Long Answer Selection with Small Data", AAAI 2019.
Paper Code
2018
Steffen Eger, Andreas Rücklé, and Iryna Gurevych: "PD3: Better Low-Resource Cross-Lingual Transfer By Combining Direct Transfer and Annotation Projection", ArgMin 2018.
Paper
Andreas Rücklé, Steffen Eger, Maxime Peyrard, and Iryna Gurevych: "Concatenated Power Mean Word Embeddings as Universal Cross-Lingual Sentence Representations", ArXiv 2018.
Paper Code
2017
Andreas Rücklé, and Iryna Gurevych: "Real-Time News Summarization with Adaptation to Media Attention", RANLP 2017.
Paper
Andreas Rücklé, and Iryna Gurevych: "Representation Learning for Answer Selection with LSTM-Based Importance Weighting", IWCS 2017.
Paper Code
Andreas Rücklé, and Iryna Gurevych: "End-to-End Non-Factoid Question Answering with an Interactive Visualization of Neural Attention Weights", ACL 2017 (Demo).
Paper Code
Michael Bugert, Yevgeniy Puzikov, Andreas Rücklé, Judith Eckle-Kohler, Teresa Martin, Eugenio Martínez-Cámara, Daniil Sorokin, Maxime Peyrard, and Iryna Gurevych: "Exploring Data Generation Methods for the Story Cloze Test", LSDSem 2017.
Paper Code