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.
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 • 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.