• Publications
  • Influence
Few-shot Natural Language Generation for Task-Oriented Dialog
TLDR
FewshotWOZ is presented, the first NLG benchmark to simulate the few-shot learning setting in task-oriented dialog systems, and the proposed SC-GPT model significantly outperforms existing methods, measured by various automatic metrics and human evaluations.
SDNet: Contextualized Attention-based Deep Network for Conversational Question Answering
TLDR
An innovated contextualized attention-based deep neural network, SDNet, to fuse context into traditional MRC models, which leverages both inter-attention and self-att attention to comprehend conversation context and extract relevant information from passage.
A Hierarchical Network for Abstractive Meeting Summarization with Cross-Domain Pretraining
TLDR
A novel abstractive summary network that adapts to the meeting scenario is proposed with a hierarchical structure to accommodate long meeting transcripts and a role vector to depict the difference among speakers.
MediaSum: A Large-scale Media Interview Dataset for Dialogue Summarization
TLDR
This paper introduces MediaSum, a large-scale media interview dataset consisting of 463.6K transcripts with abstractive summaries that can be used in transfer learning to improve a model’s performance on other dialogue summarization tasks.
Enhancing Factual Consistency of Abstractive Summarization
TLDR
A fact-aware summarization model FASum is proposed to extract and integrate factual relations into the summary generation process via graph attention and a factual corrector model FC is designed to automatically correct factual errors from summaries generated by existing systems.
Data Augmentation for Spoken Language Understanding via Pretrained Models
TLDR
A data augmentation method with pretrained language models to boost the variability and accuracy of generated utterances and investigate and propose solutions to two previously overlooked scenarios of data scarcity in SLU.
Florence: A New Foundation Model for Computer Vision
TLDR
By incorporating universal visual-language representations from Web-scale image-text data, the Florence model can be easily adapted for various computer vision tasks, such as classification, retrieval, object detection, VQA, image caption, video retrieval and action recognition.
Boosting Factual Correctness of Abstractive Summarization with Knowledge Graph
TLDR
A Fact-Aware Summarization model, FASum, is proposed, which extracts factual relations from the article to build a knowledge graph and integrates it into the neural decoding process and improves the factual correctness of summaries generated by various models via only modifying several entity tokens.
Multi-task Learning for Natural Language Generation in Task-Oriented Dialogue
TLDR
A novel multi-task learning framework, NLG-LM, for natural language generation that explicitly targets for naturalness in generated responses via an unconditioned language model, which can significantly improve the learning of style and variation in human language.
JAKET: Joint Pre-training of Knowledge Graph and Language Understanding
TLDR
A novel joint pre-training framework, JAKET, to model both the knowledge graph and language, which enables the pre-trained model to easily adapt to unseen knowledge graphs in new domains.
...
1
2
3
4
5
...