Enhancing Task-Oriented Dialogues with Chitchat: a Comparative Study Based on Lexical Diversity and Divergence

November 23, 2023 · Entered Twilight · 🏛 Automatic Speech Recognition & Understanding

Repo contents: .gitignore, README.md, compare_diversity_divergence.py, generate_accentor_seeds.py, load_utts.py, metric_utils.py, requirements.txt, utt_data

Authors Armand Stricker, Patrick Paroubek arXiv ID 2311.14067 Category cs.CL: Computation & Language Citations 1 Venue Automatic Speech Recognition & Understanding Repository https://github.com/armandstrickernlp/Task-Chitchat-Entropy Last Checked 3 months ago

Abstract

As a recent development, task-oriented dialogues (TODs) have been enriched with chitchat in an effort to make dialogues more diverse and engaging. This enhancement is particularly valuable as TODs are often confined to narrow domains, making the mitigation of repetitive and predictable responses a significant challenge. This paper presents a comparative analysis of three chitchat enhancements, aiming to identify the most effective approach in terms of diversity. Additionally, we quantify the divergence between the added chitchat, the original task-oriented language, and chitchat typically found in chitchat datasets, highlighting the top 20 divergent keywords for each comparison. Our findings drive a discussion on future enhancements for augmenting TODs, emphasizing the importance of grounding dialogues beyond the task to achieve more diverse and natural exchanges.