Survey of hallucination in natural language generation
Natural Language Generation (NLG) has improved exponentially in recent years thanks to
the development of sequence-to-sequence deep learning technologies such as Transformer …
the development of sequence-to-sequence deep learning technologies such as Transformer …
Contrastive learning reduces hallucination in conversations
Pre-trained language models (LMs) store knowledge in their parameters and can generate
informative responses when used in conversational systems. However, LMs suffer from the …
informative responses when used in conversational systems. However, LMs suffer from the …
Language models are few-shot multilingual learners
General-purpose language models have demonstrated impressive capabilities, performing
on par with state-of-the-art approaches on a range of downstream natural language …
on par with state-of-the-art approaches on a range of downstream natural language …
Transformers in speech processing: A survey
The remarkable success of transformers in the field of natural language processing has
sparked the interest of the speech-processing community, leading to an exploration of their …
sparked the interest of the speech-processing community, leading to an exploration of their …
Neural path hunter: Reducing hallucination in dialogue systems via path grounding
Dialogue systems powered by large pre-trained language models (LM) exhibit an innate
ability to deliver fluent and natural-looking responses. Despite their impressive generation …
ability to deliver fluent and natural-looking responses. Despite their impressive generation …
Towards information-rich, logical dialogue systems with knowledge-enhanced neural models
Dialogue systems have made massive promising progress contributed by deep learning
techniques and have been widely applied in our life. However, existing end-to-end neural …
techniques and have been widely applied in our life. However, existing end-to-end neural …
Please be polite: Towards building a politeness adaptive dialogue system for goal-oriented conversations
Politeness embalms interactions, putting the parties in conversation at ease. Even the most
well-intended communication can fall through if there is a manifestation of rudeness …
well-intended communication can fall through if there is a manifestation of rudeness …
Multi-task learning with graph attention networks for multi-domain task-oriented dialogue systems
M Zhao, L Wang, Z Jiang, R Li, X Lu, Z Hu - Knowledge-Based Systems, 2023 - Elsevier
A task-oriented dialogue system (TOD) is an important application of artificial intelligence. In
the past few years, works on multi-domain TODs have attracted increased research attention …
the past few years, works on multi-domain TODs have attracted increased research attention …
Conversational agents: Theory and applications
M Wahde, M Virgolin - … Volume 2: Deep Learning, Intelligent Control …, 2022 - World Scientific
In this chapter, we provide a review of conversational agents (CAs), discussing chatbots,
intended for casual conversation with a user, as well as task-oriented agents that generally …
intended for casual conversation with a user, as well as task-oriented agents that generally …
Dialokg: Knowledge-structure aware task-oriented dialogue generation
Task-oriented dialogue generation is challenging since the underlying knowledge is often
dynamic and effectively incorporating knowledge into the learning process is hard. It is …
dynamic and effectively incorporating knowledge into the learning process is hard. It is …