Coarse-to-fine knowledge selection for document grounded dialogs
Multi-document grounded dialogue systems (DGDS) belong to a class of conversational
agents that answer users' requests by finding supporting knowledge from a collection of …
agents that answer users' requests by finding supporting knowledge from a collection of …
Information-enhanced hierarchical self-attention network for multiturn dialog generation
J Wang, X Sun, Q Chen, M Wang - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
Transformer structure has shown promising results in multiturn dialog generation. The self-
attention mechanism can learn global dependencies but ignores local information, limiting …
attention mechanism can learn global dependencies but ignores local information, limiting …
Neural network with hierarchical attention mechanism for contextual topic dialogue generation
X Sun, B Ding - IEEE Access, 2022 - ieeexplore.ieee.org
The encoder-decoder model has achieved remarkable results in natural language
generation. However, in the dialogue generation work, we often ignore the influence of the …
generation. However, in the dialogue generation work, we often ignore the influence of the …
ChatMDG: A discourse parsing graph fusion based approach for multi-party dialogue generation
Comprehending multi-party dialogue generation poses a challenge due to intricate speaker
interactions, where multiple participants engage in a dynamic exchange of questions and …
interactions, where multiple participants engage in a dynamic exchange of questions and …
Revisiting conversation discourse for dialogue disentanglement
Dialogue disentanglement aims to detach the chronologically ordered utterances into
several independent sessions. Conversation utterances are essentially organized and …
several independent sessions. Conversation utterances are essentially organized and …
EAGS: An extracting auxiliary knowledge graph model in multi-turn dialogue generation
Multi-turn dialogue generation is an essential and challenging subtask of text generation in
the question answering system. Existing methods focused on extracting latent topic-level …
the question answering system. Existing methods focused on extracting latent topic-level …
Fast and Accurate Incomplete Utterance Rewriting
Omission and reference frequently occur in dialogues, which complicate the semantic
structure of the dialogue and hinder the understanding of dialogue systems. Facing the …
structure of the dialogue and hinder the understanding of dialogue systems. Facing the …
CRKG: combining retrieval knowledge with generative language models
F Chen, C Zhang, B Ning - The Journal of Supercomputing, 2025 - Springer
Multi-turn dialogue generation tasks heavily rely on capturing contextual information.
However, in real-life scenarios, capturing the speaker's needs accurately cannot be …
However, in real-life scenarios, capturing the speaker's needs accurately cannot be …
Enhancing Document Information Selection Through Multi-Granularity Responses for Dialogue Generation
M Wang, K Qiao, S Xing, C Yuan, X Wang - Neural Processing Letters, 2024 - Springer
Document information selection is an essential part of document-grounded dialogue tasks,
and more accurate information selection results can provide more appropriate dialogue …
and more accurate information selection results can provide more appropriate dialogue …
Revisiting Conversation Discourse for Dialogue Disentanglement
Dialogue disentanglement aims to detach the chronologically ordered utterances into
several independent sessions. Conversation utterances are essentially organized and …
several independent sessions. Conversation utterances are essentially organized and …