A trainable generator for recommendations in multimodal dialog
By Marilyn A. Walker, Rashmi Prasad, Amanda Stent. 2003
28 citations recorded by the source corpus.
As the complexity of spoken dialogue systems has increased, there has been increasing interest in spoken language generation (SLG). SLG promises portability across application domains and dialogue situations through the development of applicationindependent linguistic modules. However in practice, rulebased SLGs often have to be tuned to the application. Recently, a number of research groups have been developing hybrid methods for spoken language generation, combining general linguistic modules with methods for training parameters for particular applications. This paper describes the use of boosting to train a sentence planner to generate recommendations for restaurants in MATCH, a multimodal dialogue system providing entertainment information for New York.
Subfields: Artificial Intelligence, Multimodal Learning, Dialogue & Conversational AI, Recommender Systems
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
- Jason Aaron Edward Weston
- Jianfeng Gao
- Mohit Bansal
- Kyunghyun Cho
- Yoshua Bengio
- Percy Liang
- Luke S. Zettlemoyer
- Yejin Choi
In Multimodal Learning
- Jason Aaron Edward Weston
- Jianfeng Gao
- Antoine Bordes
- Michel Galley
- Michael Auli
- Arthur Szlam
- Margaret Mitchell
- Devi Parikh
In Dialogue & Conversational AI
- Jason Aaron Edward Weston
- Jianfeng Gao
- Michel Galley
- Alexander H. Miller
- Antoine Bordes
- Xiang Zhang
- Michael Auli
- Andreea Gane
In Recommender Systems
Citations in the corpus
- A Neural Network Approach to Context-Sensitive Generation of Conversational Responses (2015, methodology): “While there are previous uses of machine learning for response generation (Walker et al., 2003), dialog state tracking (Young et al.”
- Evaluating Prerequisite Qualities for Learning End-to-End Dialog Systems (2015, background): “Because of language ambiguity and variation, evaluation of the response generation step is complicated and usually relies on human judgement (Walker et al., 2003).”