no code implementations • EMNLP 2021 • Tobias Falke, Patrick Lehnen
With counterfactual bandit learning, models can be trained based on positive and negative feedback received for historical predictions, with no labeled data needed.
Multi-agent Reinforcement Learning
Reinforcement Learning (RL)
+1
no code implementations • EMNLP (NLP4ConvAI) 2021 • Subhadarshi Panda, Caglar Tirkaz, Tobias Falke, Patrick Lehnen
As a solution, we propose a multilingual paraphrase generation model that can be used to generate novel utterances for a target feature and target language.
no code implementations • 14 Jun 2023 • Saleh Soltan, Andy Rosenbaum, Tobias Falke, Qin Lu, Anna Rumshisky, Wael Hamza
(2) Conversely, using an encoder to warm-start seq2seq training, we show that by unfreezing the encoder partway through training, we can match task performance of a from-scratch seq2seq model.
no code implementations • COLING 2020 • Shailza Jolly, Tobias Falke, Caglar Tirkaz, Daniil Sorokin
Recent progress through advanced neural models pushed the performance of task-oriented dialog systems to almost perfect accuracy on existing benchmark datasets for intent classification and slot labeling.
no code implementations • COLING 2020 • Tobias Falke, Markus Boese, Daniil Sorokin, Caglar Tirkaz, Patrick Lehnen
In large-scale commercial dialog systems, users express the same request in a wide variety of alternative ways with a long tail of less frequent alternatives.
no code implementations • ACL 2019 • Tobias Falke, Leonardo F. R. Ribeiro, Prasetya Ajie Utama, Ido Dagan, Iryna Gurevych
While recent progress on abstractive summarization has led to remarkably fluent summaries, factual errors in generated summaries still severely limit their use in practice.
Abstractive Text Summarization
Natural Language Inference
+1
1 code implementation • NAACL 2019 • Tobias Falke, Iryna Gurevych
Concept map-based multi-document summarization has recently been proposed as a variant of the traditional summarization task with graph-structured summaries.
no code implementations • IJCNLP 2017 • Tobias Falke, Christian M. Meyer, Iryna Gurevych
Concept-map-based multi-document summarization is a variant of traditional summarization that produces structured summaries in the form of concept maps.
no code implementations • EMNLP 2017 • Tobias Falke, Iryna Gurevych
Many techniques to automatically extract different types of graphs, showing for example entities or concepts and different relationships between them, have been suggested.
1 code implementation • EMNLP 2017 • Tobias Falke, Iryna Gurevych
Concept maps can be used to concisely represent important information and bring structure into large document collections.