AI Seminar Series 2023: Maliha Sultana

The AI Seminar is a weekly meeting at the University of Alberta where researchers interested in artificial intelligence (AI) can share their research. Presenters include both local speakers from the University of Alberta and visitors from other institutions. Topics can be related in any way to artificial intelligence, from foundational theoretical work to innovative applications of AI techniques to new fields and problems.

On June 23rd, Maliha Sultana —a recent Master's graduate at the University of Alberta — presented “An Exploration of Dialog Act Classification in Open-domain Conversational Agents and the Applicability of Text Data Augmentation" at the AI Seminar.

Recognizing dialog acts of users is an essential component in building successful conversational agents. In this work, Sultana and her team propose a dialog act (DA) classifier for two of their open domain conversational agents. For this, they curated a high-quality, multi-domain dataset with ∼24k user utterances labelled into 8 suitable DAs. The fine-tuned BERT-based model outperforms the baseline SVM classifier by achieving state-of-the-art accuracy on the proposed dataset. Moreover, it generalizes well on unseen data. To address the issue of data scarcity when training DA classifiers, Sultana implemented different data augmentation techniques and compared their performance. Extensive experiments show that, in a simulated low data regime with only 10 examples per label, methods as simple as synonym replacement can double the size of the existing training data and boost accuracy of our DA classifier by ∼8%. Lastly, Sultana demonstrates how the proposed classifier and augmentation techniques can be adapted to effectively detect dialog acts in languages other than English.

Watch the full presentation below:

Want to learn how you can kick-start your AI career? Find out more about Amii's Career Accelerator to find out more.