Tobias Falke

Researcher, Natural Language Processing

Short Bio

I did a PhD in computer science at UKP Lab and AIPHES at Technische Universität Darmstadt, Germany, working on natural language processing. The goal of my research was to simplify browsing and exploring large collections of documents. I worked on automatic text summarization, information extraction, deep learning and interactive learning to build tools towards that goal.

From April to June 2018, I interned in Google's NYC office and worked on natural language understanding for Google Assistant. In March 2019, I joined Amazon's Alexa AI group as an Applied Scientist. I'm currently working from Berlin, Germany.

For a more comprehensive bio, please check out my LinkedIn profile.

Publications

Recipes for Sequential Pre-training of Multilingual Encoder and Seq2Seq Models

Saleh Soltan, Andy Rosenbaum, Tobias Falke, Qin Lu, Anna Rumshisky and Wael Hamza

Findings of the Association for Computational Linguistics: ACL 2023. Toronto, Canada. July 2023.

Regression-Free Model Updates for Spoken Language Understanding

Andrea Caciolai, Verena Weber, Tobias Falke, Alessandro Pedrani and Davide Bernardi

Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 5: Industry Track). Toronto, Canada. July 2023.

Sharing Encoder Representations across Languages, Domains and Tasks in Large-Scale Spoken Language Understanding

Jonathan Hueser, Judith Gaspers, Thomas Gueudre, Chandana Prakash, Jin Cao, Daniil Sorokin, Quynh Do, Nicolas Anastassacos, Tobias Falke, Turan Gojayev, Mariusz Momotko, Denis Romasanta Rodriguez, Austin Doolittle, Kartik Balasubramaniam, Wael Hamza, Fabian Triefenbach and Patrick Lehnen

Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 5: Industry Track). Toronto, Canada. July 2023.

Feedback Attribution for Counterfactual Bandit Learning in Multi-Domain Spoken Language Understanding

Tobias Falke and Patrick Lehnen

Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. Virtual. November 2021.

Multilingual Paraphrase Generation For Bootstrapping New Features in Task-Oriented Dialog Systems

Subhadarshi Panda, Caglar Tirkaz, Tobias Falke and Patrick Lehnen

Proceedings of the 3rd Workshop on Natural Language Processing for Conversational AI. Virtual. November 2021.

Leveraging User Paraphrasing Behavior In Dialog Systems To Automatically Collect Annotations For Long-Tail Utterances

Tobias Falke, Markus Boese, Daniil Sorokin, Caglar Tirkaz and Patrick Lehnen

28th International Conference on Computational Linguistics. Virtual. December 2020.
Best Paper Award — Industry Track

Data-Efficient Paraphrase Generation to Bootstrap Intent Classification and Slot Labeling for New Features in Task-Oriented Dialog Systems

Shailza Jolly, Tobias Falke, Caglar Tirkaz and Daniil Sorokin

28th International Conference on Computational Linguistics. Virtual. December 2020.

Ranking Generated Summaries by Correctness: An Interesting but Challenging Application for Natural Language Inference

Tobias Falke, Leonardo F. R. Ribeiro, Prasetya Ajie Utama, Ido Dagan and Iryna Gurevych

57th Annual Meeting of the Association for Computational Linguistics. Florence, Italy. July 2019.

Fast Concept Mention Grouping for Concept-Map-Based Multi-Document Summarization

Tobias Falke and Iryna Gurevych

Annual Conference of the North American Chapter of the Association for Computational Linguistics. Minneapolis, MN, USA. June 2019.

Automatic Structured Text Summarization with Concept Maps

Tobias Falke

PhD Thesis, Technische Universität Darmstadt, Germany. January 2019.

What's Important in a Text? An Extensive Evaluation of Linguistic Annotations for Summarization

Markus Zopf, Teresa Botschen, Tobias Falke, Benjamin Heinzerling, Ana Marasovic, Todor Mihaylov, P.V.S. Avinesh, Eneldo Loza Mencia, Johannes Fürnkranz and Anette Frank

Fifth International Conference on Social Networks Analysis, Management and Security (SNAMS). Valencia, Spain. October 2018.

Concept-Map-Based Multi-Document Summarization using Concept Coreference Resolution and Global Importance Optimization

Tobias Falke, Christian M. Meyer and Iryna Gurevych

8th International Joint Conference on Natural Language Processing (IJCNLP). Taipei, Taiwan. November 2017.

Bringing Structure into Summaries: Crowdsourcing a Benchmark Corpus of Concept Maps

Tobias Falke and Iryna Gurevych

Conference on Empirical Methods in Natural Language Processing (EMNLP). Copenhagen, Denmark. September 2017.
Best Resource Paper Award

GraphDocExplore: A Framework for the Experimental Comparison of Graph-based Document Exploration Techniques

Tobias Falke and Iryna Gurevych

Conference on Empirical Methods in Natural Language Processing (EMNLP). Copenhagen, Denmark. September 2017.

Utilizing Automatic Predicate-Argument Analysis for Concept Map Mining

Tobias Falke and Iryna Gurevych

12th International Conference on Computational Semantics (IWCS). Montpellier, France. September 2017.

Porting an Open Information Extraction System from English to German

Tobias Falke, Gabriel Stanovsky, Iryna Gurevych and Ido Dagan

Conference on Empirical Methods in Natural Language Processing (EMNLP). Austin, TX, USA. November 2016.