Comparing Chatbot Performance Enhanced with Persistent Homology
For developers of domain-specific chatbots with limited data, this offers a low-cost method to potentially improve performance without increasing dataset size.
This work enhances chatbot input datasets using persistent homology vectorizations and compares performance across multiple metrics. Results show that while not always beneficial, the enhancement can bring remarkable advantages at virtually no cost.
Chatbots have become increasingly prevalent across various domains, offering automated assistance in many areas, especially mental health support. The training is done using extremely large datasets, which are sometimes not available in very specific domains. Moreover, it would sometimes be ideal to train the chatbot with personal information about the patients, which, of course, cannot be done on shared servers since it would violate patient confidentiality. Hence, being able to improve the performance of a chatbot, possibly trained locally and on a restricted dataset, without having to increase the dataset itself, would be extremely beneficial. In this work, we will enhance the input datasets using persistent homology (PH) vectorizations computed from the raw datasets themselves. Then we will compare, across several metrics, the performance of multiple chatbot models with or without the PH enhancement. Our experiments suggest that, while at times the PH enhancement is not particularly beneficial, it sometimes brings remarkable advantages for virtually no cost.