research
∙
05/22/2023
MADNet: Maximizing Addressee Deduction Expectation for Multi-Party Conversation Generation
Modeling multi-party conversations (MPCs) with graph neural networks has...
share
research
∙
05/19/2023
DiffuSIA: A Spiral Interaction Architecture for Encoder-Decoder Text Diffusion
Diffusion models have emerged as the new state-of-the-art family of deep...
research
∙
03/16/2022
TegTok: Augmenting Text Generation via Task-specific and Open-world Knowledge
Generating natural and informative texts has been a long-standing proble...
research
∙
03/16/2022
HeterMPC: A Heterogeneous Graph Neural Network for Response Generation in Multi-Party Conversations
Recently, various response generation models for two-party conversations...
research
∙
01/26/2022
Neural Grapheme-to-Phoneme Conversion with Pre-trained Grapheme Models
Neural network models have achieved state-of-the-art performance on grap...
research
∙
10/06/2021
PoNet: Pooling Network for Efficient Token Mixing in Long Sequences
Transformer-based models have achieved great success in various NLP, vis...
research
∙
12/22/2020