Results 1 to 10 of about 572,188 (337)
Complementary Therapies in Medicine, 2004 Conversation analysis (CA) is well established as a means of exploring the interactional detail of conventional healthcare encounters. It is also becoming increasingly popular in action to CAM. This article outlines the main features of CA, how it can be used in a CAM context, and the type of information it can be expected to reveal.
Steven E. Clayman, Virginia Teas Gill
semanticscholar +4 more sources
Retrieval Augmentation Reduces Hallucination in Conversation [PDF]
Conference on Empirical Methods in Natural Language Processing, 2021 Despite showing increasingly human-like conversational abilities, state-of-the-art dialogue models often suffer from factual incorrectness and hallucination of knowledge (Roller et al., 2020).
Kurt Shuster +4 more
semanticscholar +1 more source
MMGCN: Multimodal Fusion via Deep Graph Convolution Network for Emotion Recognition in Conversation [PDF]
Annual Meeting of the Association for Computational Linguistics, 2021 Emotion recognition in conversation (ERC) is a crucial component in affective dialogue systems, which helps the system understand users’ emotions and generate empathetic responses.
Jingwen Hu +3 more
semanticscholar +1 more source
Beyond Goldfish Memory: Long-Term Open-Domain Conversation [PDF]
Annual Meeting of the Association for Computational Linguistics, 2021 Despite recent improvements in open-domain dialogue models, state of the art models are trained and evaluated on short conversations with little context. In contrast, the long-term conversation setting has hardly been studied. In this work we collect and
Jing Xu, Arthur Szlam, J. Weston
semanticscholar +1 more source
PLACES: Prompting Language Models for Social Conversation Synthesis [PDF]
Findings, 2023 Collecting high quality conversational data can be very expensive for most applications and infeasible for others due to privacy, ethical, or similar concerns.
Maximillian Chen +7 more
semanticscholar +1 more source
Epistemically violent biases in artificial intelligence design: the case of DALLE-E 2 and Starry AI [PDF]
Digital Transformation and Society, 2023 Purpose – The paper aims to expand on the works well documented by Joy Boulamwini and Ruha Benjamin by expanding their critique to the African continent. The research aims to assess if algorithmic biases are prevalent in DALL-E 2 and Starry AI.
Blessing Mbalaka
doaj +1 more source
GCNet: Graph Completion Network for Incomplete Multimodal Learning in Conversation [PDF]
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022 Conversations have become a critical data format on social media platforms. Understanding conversation from emotion, content and other aspects also attracts increasing attention from researchers due to its widespread application in human-computer ...
Zheng Lian +4 more
semanticscholar +1 more source
DEVELOPMENTAL STATE AND THE QUESTION OF ACCOUNTABILITY
Journal of Social Political Sciences, 2023 In South Africa, despite what appears to be a perfectly designed political system underpinned by the separation of powers, there seemingly is a lack of accountability of public officials that has its roots in the proportional representation (PR ...
Vusimuzi Gumbi, Keaobaka Tsholo
doaj +1 more source
Agronomy, 2023 Changing electrical environments can influence the performance of herbivorous insects and adversely affect their control strategies. The diamondback moth, Plutella xylostella (L.), is a pest that devastates cruciferous vegetables.
Li Jia +7 more
doaj +1 more source
African Journal of Gender and Religion (AJGR), 2021 This article explores the metaphor of midwife as a statement of position for supporting pastoral and self-care during Covid-19 times. It weaves collabora-tive threads of narrative therapy, feminism, and pastoral theology to explore meaning-making, the ...
Nicole Dickson
doaj +1 more source