Put Chatbot into Its Interlocutor's Shoes: New Framework to Learn Chatbot Responding with Intention
This addresses the limitation of chatbots in understanding and influencing human interlocutors, though it is an incremental step in making chatbots more human-like.
The paper tackles the problem of chatbots lacking human-like intention in responses by proposing a framework where a guiding chatbot learns to induce specific responses from an interlocutor model, such as joyful or long replies, and demonstrates effectiveness through experiments with both models and human trials.
Most chatbot literature that focuses on improving the fluency and coherence of a chatbot, is dedicated to making chatbots more human-like. However, very little work delves into what really separates humans from chatbots -- humans intrinsically understand the effect their responses have on the interlocutor and often respond with an intention such as proposing an optimistic view to make the interlocutor feel better. This paper proposes an innovative framework to train chatbots to possess human-like intentions. Our framework includes a guiding chatbot and an interlocutor model that plays the role of humans. The guiding chatbot is assigned an intention and learns to induce the interlocutor to reply with responses matching the intention, for example, long responses, joyful responses, responses with specific words, etc. We examined our framework using three experimental setups and evaluated the guiding chatbot with four different metrics to demonstrate flexibility and performance advantages. Additionally, we performed trials with human interlocutors to substantiate the guiding chatbot's effectiveness in influencing the responses of humans to a certain extent. Code will be made available to the public.