Combining Textual Content and Structure to Improve Dialog Similarity
This work addresses the challenge of improving chatbot development by providing a better method for analyzing dialog data, though it is incremental as it builds on existing similarity measures.
The paper tackled the problem of measuring dialog similarity by proposing a new metric that incorporates both textual content and dialog structure, and demonstrated that this combined approach yields more accurate results than using either measure alone on the Switchboard dataset.
Chatbots, taking advantage of the success of the messaging apps and recent advances in Artificial Intelligence, have become very popular, from helping business to improve customer services to chatting to users for the sake of conversation and engagement (celebrity or personal bots). However, developing and improving a chatbot requires understanding their data generated by its users. Dialog data has a different nature of a simple question and answering interaction, in which context and temporal properties (turn order) creates a different understanding of such data. In this paper, we propose a novelty metric to compute dialogs' similarity based not only on the text content but also on the information related to the dialog structure. Our experimental results performed over the Switchboard dataset show that using evidence from both textual content and the dialog structure leads to more accurate results than using each measure in isolation.