Lexical Acquisition through Implicit Confirmations over Multiple Dialogues

By Kohei Ono, Ryu Takeda, Eric Nichols, Mikio Nakano, Kazunori Komatani. 2017

15 citations recorded by the source corpus.

We address the problem of acquiring the ontological categories of unknown terms through implicit confirmation in dialogues. We develop an approach that makes implicit confirmation requests with an unknown term’s predicted category. Our approach does not degrade user experience with repetitive explicit confirmations, but the system has difficulty determining if information in the confirmation request can be correctly acquired. To overcome this challenge, we propose a method for determining whether or not the predicted category is correct, which is included in an implicit confirmation request. Our method exploits multiple user responses to implicit confirmation requests containing the same ontological category. Experimental results revealed that the proposed method exhibited a higher precision rate for determining the correctly predicted categories than when only single user responses were considered.

Subfields: Artificial Intelligence

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

1. Bing Liu
2. Sahisnu Mazumder
3. Shuai Wang
4. Nianzu Ma
5. Zixuan Ke
6. C. Mei
7. Hu Xu
8. Lei Shu

Citations in the corpus

• Lifelong and Continual Learning Dialogue Systems: Learning during Conversation (2021, background): “Otsuka et al. (2013) and Ono et al. (2017) have explored the problem of lexical acquisition during dialogues.”
• Lifelong Knowledge Learning in Rule-based Dialogue Systems (2020, background): “The work in (Otsuka et al., 2013; Ono et al., 2017) asks the user whether the system’s prediction of category of a term is correct or not.”
• Lifelong and Interactive Learning of Factual Knowledge in Dialogues (2019, background): “Ono et al. (2017), Otsuka et al. (2013), Ono et al. (2016) and Komatani et al. (2016) allow a system to ask the user whether its prediction of category of a term is correct or not.”
• Lifelong Learning Dialogue Systems: Chatbots that Self-Learn On the Job (2020, background): “Otsuka et al. (2013) and Ono et al. (2016, 2017) have explored the problem of lexical acquisition during dialogues in closed-domain chatbots.”
• Continuous and Interactive Factual Knowledge Learning in Verification Dialogues (2020, background): “[38, 39] studied lexical knowledge acquisition in dialogues, whereas IKAI is about interactive factual knowledge learning and inference.”