Communicative Grounding of Analogical Explanations in Dialogue: A Corpus Study of Conversational Management Acts and Statistical Sequence Models for Tutoring through Analogy

Jorge Del-Bosque-Trevino, Julian Hough, Matthew Purver


Abstract
We present a conversational management act (CMA) annotation schema for one-to-one tutorial dialogue sessions where a tutor uses an analogy to teach a student a concept. CMAs are more fine-grained sub-utterance acts compared to traditional dialogue act mark-up. The schema achieves an inter-annotator agreement (IAA) Cohen Kappa score of at least 0.66 across all 10 classes. We annotate a corpus of analogical episodes with the schema and develop statistical sequence models from the corpus which predict tutor content related decisions, in terms of the selection of the analogical component (AC) and tutor conversational management act (TCMA) to deploy at the current utterance, given the student’s behaviour. CRF sequence classifiers perform well on AC selection and robustly on TCMA selection, achieving respective accuracies of 61.9% and 56.3% on a cross-validation experiment over the corpus.
Anthology ID:
2021.reinact-1.4
Volume:
Proceedings of the Reasoning and Interaction Conference (ReInAct 2021)
Month:
October
Year:
2021
Address:
Gothenburg, Sweden
Venue:
ReInAct
SIG:
SIGSEM
Publisher:
Association for Computational Linguistics
Note:
Pages:
23–31
Language:
URL:
https://aclanthology.org/2021.reinact-1.4
DOI:
Bibkey:
Copy Citation:
PDF:
https://aclanthology.org/2021.reinact-1.4.pdf