667 citations · 811 across the 12 of their papers we have counts for
10 papers · 1 filter
WeLM: A Well-Read Pre-trained Language Model for Chinese
Hui Su, Xiao Zhou, Houjin Yu +5
Large Language Models pre-trained with self-supervised learning have demonstrated impressive zero-shot generalization capabilities on a wide spectrum of tasks. In this work, we pre…
Neural Data-to-Text Generation with LM-based Text Augmentation
Ernie Chang, Xiaoyu Shen, Dawei Zhu +2
For many new application domains for data-to-text generation, the main obstacle in training neural models consists of a lack of training data. While usually large numbers of instan…
Diversifying Dialogue Generation with Non-Conversational Text
Hui Su, Xiaoyu Shen, Sanqiang Zhao +5
Neural network-based sequence-to-sequence (seq2seq) models strongly suffer from the low-diversity problem when it comes to open-domain dialogue generation. As bland and generic utt…
Neural Data-to-Text Generation via Jointly Learning the Segmentation and Correspondence
Xiaoyu Shen, Ernie Chang, Hui Su +2
The neural attention model has achieved great success in data-to-text generation tasks. Though usually excelling at producing fluent text, it suffers from the problem of informatio…
Select and Attend: Towards Controllable Content Selection in Text Generation
Xiaoyu Shen, Jun Suzuki, Kentaro Inui +3
Many text generation tasks naturally contain two steps: content selection and surface realization. Current neural encoder-decoder models conflate both steps into a black-box archit…
Improving Multi-turn Dialogue Modelling with Utterance ReWriter
Hui Su, Xiaoyu Shen, Rongzhi Zhang +4
Recent research has made impressive progress in single-turn dialogue modelling. In the multi-turn setting, however, current models are still far from satisfactory. One major challe…
NEXUS Network: Connecting the Preceding and the Following in Dialogue Generation
Hui Su, Xiaoyu Shen, Wenjie Li +1
Sequence-to-Sequence (seq2seq) models have become overwhelmingly popular in building end-to-end trainable dialogue systems. Though highly efficient in learning the backbone of huma…
Improving Variational Encoder-Decoders in Dialogue Generation
Xiaoyu Shen, Hui Su, Shuzi Niu +1
Variational encoder-decoders (VEDs) have shown promising results in dialogue generation. However, the latent variable distributions are usually approximated by a much simpler model…
DailyDialog: A Manually Labelled Multi-turn Dialogue Dataset
Yanran Li, Hui Su, Xiaoyu Shen +3
We develop a high-quality multi-turn dialog dataset, DailyDialog, which is intriguing in several aspects. The language is human-written and less noisy. The dialogues in the dataset…
A Conditional Variational Framework for Dialog Generation
Xiaoyu Shen, Hui Su, Yanran Li +5
Deep latent variable models have been shown to facilitate the response generation for open-domain dialog systems. However, these latent variables are highly randomized, leading to…