Towards end-to-end multi-domain dialogue modelling
By Paweł Budzianowski, Iñigo Casanueva, B-H Tseng, Milica Gasic. 2018
18 citations recorded by the source corpus.
Subfields: Artificial Intelligence, Natural Language Processing
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Minlie Huang
- Jianfeng Gao
- Richard Socher
- Andrea Madotto
- Ivan Vulic
- Caiming Xiong
- Xiaoyan Zhu
- Pascale Fung
In Natural Language Processing
- Jianfeng Gao
- Minlie Huang
- Richard Socher
- Ivan Vulic
- Andrea Madotto
- Caiming Xiong
- Xiaoyan Zhu
- Chien-Sheng Wu
Citations in the corpus
- A Simple Language Model for Task-Oriented Dialogue (2020, methodology): “Robustness to Noisy Annotations To understand the source of dialogue state tracking errors, we investigated MultiWOZ 2.1 annotations in depth.”
- MultiWOZ - A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling (2018, background): “Figure 4 presents the architecture of the system (Budzianowski et al., 2018).”
- Hello, It’s GPT-2 - How Can I Help You? Towards the Use of Pretrained Language Models for Task-Oriented Dialogue Systems (2019, methodology): “To evaluate the ability of transferring the GPT generation capability to constrained/focused dialogue tasks and domains, we rely on the multi-domain MultiWOZ dataset (Budzianowski et al., 2018b).”
- ConvLab-2: An Open-Source Toolkit for Building, Evaluating, and Diagnosing Dialogue Systems (2020, methodology): “MDRG is the baseline model proposed by Budzianowski et al. (2018b) on MultiWOZ, while HDSA and LaRL achieve much stronger performance on this dataset.”