An Empirical Study of Topic Transition in Dialogue
This work addresses the challenge of emulating human-like topic transitions in open-domain dialog systems, though it is incremental as it builds on existing corpus-based studies.
The study tackled the problem of understanding and modeling topic transitions in human dialogue by annotating 215 conversations from the Switchboard corpus and analyzing variables like length and turns per topic, achieving a precision of 83% on in-domain and 82% on out-of-domain test sets.
Transitioning between topics is a natural component of human-human dialog. Although topic transition has been studied in dialogue for decades, only a handful of corpora based studies have been performed to investigate the subtleties of topic transitions. Thus, this study annotates 215 conversations from the switchboard corpus and investigates how variables such as length, number of topic transitions, topic transitions share by participants and turns/topic are related. This work presents an empirical study on topic transition in switchboard corpus followed by modelling topic transition with a precision of 83% for in-domain(id) test set and 82% on 10 out-of-domain}(ood) test set. It is envisioned that this work will help in emulating human-human like topic transition in open-domain dialog systems.