Emotion-and-knowledge grounded response generation in an open-domain dialogue setting

Article Computer Science, Artificial Intelligence

Recent advances in deep learning based dialogue systems: a systematic survey

Jinjie Ni et al.

Summary: This article surveys deep learning based dialogue systems, comprehensively reviewing and analyzing the state-of-the-art research outcomes in this field. It discusses different models in terms of principles, characteristics, and applications, and explores task-oriented and open-domain dialogue systems as two streams of research. The article also reviews evaluation methods and datasets for dialogue systems, and identifies possible future research trends.

ARTIFICIAL INTELLIGENCE REVIEW (2023)

Add to Collection

Article Computer Science, Artificial Intelligence

Will Affective Computing Emerge From Foundation Models and General Artificial Intelligence? A First Evaluation of ChatGPT

Mostafa Amin et al.

Summary: ChatGPT demonstrates the potential of general artificial intelligence capabilities and performs well across various natural language processing tasks. This study evaluates ChatGPT's text classification abilities for affective computing problems including personality prediction, sentiment analysis, and suicide tendency detection. Results show that task-specific RoBERTa models generally outperform other baselines, while ChatGPT performs decently and is comparable to Word2Vec and BoW baselines. ChatGPT exhibits robustness against noisy data, outperforming Word2Vec in such scenarios. The study concludes that ChatGPT is a good generalist model but not as specialized as task-specific models for optimal performance.

IEEE INTELLIGENT SYSTEMS (2023)

Add to Collection

Article Computer Science, Artificial Intelligence

Multitask learning for multilingual intent detection and slot filling in dialogue systems

Mauajama Firdaus et al.

Summary: This research proposes a multilingual multitask approach that improves intent accuracy and slot filling for three different languages. The experimental results show an improvement in both tasks for all languages.

INFORMATION FUSION (2023)

Add to Collection

Article Multidisciplinary Sciences

EmoKbGAN: Emotion controlled response generation using Generative Adversarial Network for knowledge grounded conversation

Deeksha Varshney et al.

Summary: Neural open-domain dialogue systems often struggle to engage users in long-term interactions on popular topics. To address this, we propose EmoKbGAN, a method that utilizes the Generative Adversarial Network (GAN) to generate automatic responses for more socially engaging conversations. Experimental results demonstrate that our method significantly improves performance over baseline models in terms of both automated and human evaluation metrics, producing fluent sentences with better control over emotion and content quality.

PLOS ONE (2023)

Add to Collection

Article Computer Science, Information Systems