๐Ÿชด Hayul's digital garden

Search

Search IconIcon to open search

Call for Customized Conversation-Customized Conversation Grounding Persona and Knowledge

Last updated May 2, 2023 Edit Source

# Abstarct

Humans usually have conversations by making use of prior knowledge about a topic and background information of the people whom they are talking to. However, existing conversational agents and datasets do not consider such comprehensive information, and thus they have a limitation in generating the utterances where the knowledge and persona are fused properly. To address this issue, we introduce a call For Customized conversation (FoCus) dataset where the customized answers are built with the userโ€™s persona and Wikipedia knowledge. (…)

We examine whether the model reflects adequate persona and knowledge with our proposed two sub-tasks, persona grounding (PG) and knowledge grounding (KG).

# FoCus Dataset

Figure 2: Example dialog between Human and Machine in FoCus dataset

# Model

We introduce the baseline models trained on our FoCus dataset, consisting of a retrieval module and a dialog module. The retrieval module retrieves the knowledge paragraphs related to a question, and the dialog module generates utterances of the machine by taking the retrieved knowledge paragraphs, humanโ€™s persona, and previous utterances as inputs.

Table 3: Experimental results

# Conclusion

We hope that the researches aim to make dialog agents more attractive and knowledgeable with grounding abilities to be explored.