Zobrazeno 1 - 10
of 291
pro vyhledávání: '"Geishauser A"'
Autor:
Feng, Shutong, Lin, Hsien-chin, Geishauser, Christian, Lubis, Nurul, van Niekerk, Carel, Heck, Michael, Ruppik, Benjamin, Vukovic, Renato, Gašić, Milica
Emotions are indispensable in human communication, but are often overlooked in task-oriented dialogue (ToD) modelling, where the task success is the primary focus. While existing works have explored user emotions or similar concepts in some ToD tasks
Externí odkaz:
http://arxiv.org/abs/2408.02417
Autor:
van Niekerk, Carel, Geishauser, Christian, Heck, Michael, Feng, Shutong, Lin, Hsien-chin, Lubis, Nurul, Ruppik, Benjamin, Vukovic, Renato, Gašić, Milica
Supervised neural approaches are hindered by their dependence on large, meticulously annotated datasets, a requirement that is particularly cumbersome for sequential tasks. The quality of annotations tends to deteriorate with the transition from expe
Externí odkaz:
http://arxiv.org/abs/2310.08944
Autor:
Feng, Shutong, Lubis, Nurul, Ruppik, Benjamin, Geishauser, Christian, Heck, Michael, Lin, Hsien-chin, van Niekerk, Carel, Vukovic, Renato, Gašić, Milica
Emotion recognition in conversations (ERC) is a crucial task for building human-like conversational agents. While substantial efforts have been devoted to ERC for chit-chat dialogues, the task-oriented counterpart is largely left unattended. Directly
Externí odkaz:
http://arxiv.org/abs/2308.12648
Autor:
Lin, Hsien-Chin, Feng, Shutong, Geishauser, Christian, Lubis, Nurul, van Niekerk, Carel, Heck, Michael, Ruppik, Benjamin, Vukovic, Renato, Gašić, Milica
Existing user simulators (USs) for task-oriented dialogue systems only model user behaviour on semantic and natural language levels without considering the user persona and emotions. Optimising dialogue systems with generic user policies, which canno
Externí odkaz:
http://arxiv.org/abs/2306.01579
Autor:
Heck, Michael, Lubis, Nurul, Ruppik, Benjamin, Vukovic, Renato, Feng, Shutong, Geishauser, Christian, Lin, Hsien-Chin, van Niekerk, Carel, Gašić, Milica
Recent research on dialogue state tracking (DST) focuses on methods that allow few- and zero-shot transfer to new domains or schemas. However, performance gains heavily depend on aggressive data augmentation and fine-tuning of ever larger language mo
Externí odkaz:
http://arxiv.org/abs/2306.01386
Autor:
Zhu, Qi, Geishauser, Christian, Lin, Hsien-chin, van Niekerk, Carel, Peng, Baolin, Zhang, Zheng, Heck, Michael, Lubis, Nurul, Wan, Dazhen, Zhu, Xiaochen, Gao, Jianfeng, Gašić, Milica, Huang, Minlie
Task-oriented dialogue (TOD) systems function as digital assistants, guiding users through various tasks such as booking flights or finding restaurants. Existing toolkits for building TOD systems often fall short of in delivering comprehensive arrays
Externí odkaz:
http://arxiv.org/abs/2211.17148
Autor:
Lubis, Nurul, Geishauser, Christian, Lin, Hsien-Chin, van Niekerk, Carel, Heck, Michael, Feng, Shutong, Gašić, Milica
Task-oriented dialogue systems aim to fulfill user goals through natural language interactions. They are ideally evaluated with human users, which however is unattainable to do at every iteration of the development phase. Simulated users could be an
Externí odkaz:
http://arxiv.org/abs/2209.00876
Autor:
Lin, Hsien-Chin, Geishauser, Christian, Feng, Shutong, Lubis, Nurul, van Niekerk, Carel, Heck, Michael, Gašić, Milica
User simulators (USs) are commonly used to train task-oriented dialogue systems (DSs) via reinforcement learning. The interactions often take place on semantic level for efficiency, but there is still a gap from semantic actions to natural language,
Externí odkaz:
http://arxiv.org/abs/2208.10817
Autor:
Geishauser, Christian, van Niekerk, Carel, Lubis, Nurul, Heck, Michael, Lin, Hsien-Chin, Feng, Shutong, Gašić, Milica
Continual learning is one of the key components of human learning and a necessary requirement of artificial intelligence. As dialogue can potentially span infinitely many topics and tasks, a task-oriented dialogue system must have the capability to c
Externí odkaz:
http://arxiv.org/abs/2204.05928
Autor:
Heck, Michael, Lubis, Nurul, van Niekerk, Carel, Feng, Shutong, Geishauser, Christian, Lin, Hsien-Chin, Gašić, Milica
Generalising dialogue state tracking (DST) to new data is especially challenging due to the strong reliance on abundant and fine-grained supervision during training. Sample sparsity, distributional shift and the occurrence of new concepts and topics
Externí odkaz:
http://arxiv.org/abs/2202.03354