Profiles2020-2023
Michael Zeng
Microsoft Azure AI
24Papers
15Last author
50Unique co-authors
0First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers24
- Automatic Prompt Optimization with "Gradient Descent" and Beam SearchAuthor 6 of 6EMNLP 2023 · 137 citations
- i-Code: An Integrative and Composable Multimodal Learning FrameworkAuthor 19 of 20AAAI 2023 · 53 citations
- ComSL: A Composite Speech-Language Model for End-to-End Speech-to-Text TranslationAuthor 6 of 7NeurIPS 2023 · 21 citations
- InheritSumm: A General, Versatile and Compact Summarizer by Distilling from GPTAuthor 7 of 7EMNLP Findings 2023 · 7 citations
- LMGQS: A Large-scale Dataset for Query-focused SummarizationAuthor 9 of 9EMNLP Findings 2023
- ReCo: Region-Controlled Text-to-Image GenerationAuthor 10 of 11CVPR 2023
- An Empirical Study of Training End-to-End Vision-and-Language TransformersAuthor 12 of 12CVPR 2022 · 313 citations
- JAKET: Joint Pre-training of Knowledge Graph and Language UnderstandingAuthor 4 of 4AAAI 2022 · 171 citations
- DialogLM: Pre-trained Model for Long Dialogue Understanding and SummarizationAuthor 5 of 5AAAI 2022 · 150 citations
- Training Data is More Valuable than You Think: A Simple and Effective Method by Retrieving from Training DataAuthor 8 of 8ACL 2022 · 115 citations
- CLIP-Event: Connecting Text and Images with Event StructuresAuthor 7 of 9CVPR 2022 · 103 citations
- End-to-End Segmentation-based News SummarizationAuthor 3 of 3ACL Findings 2022 · 21 citations
- Unsupervised Multi-Granularity SummarizationAuthor 9 of 11EMNLP Findings 2022 · 12 citations
- Leveraging Knowledge in Multilingual Commonsense ReasoningAuthor 7 of 7ACL Findings 2022 · 11 citations
- Task Compass: Scaling Multi-task Pre-training with Task PrefixAuthor 9 of 9EMNLP Findings 2022 · 11 citations
- Automatic Rule Induction for Efficient Semi-Supervised LearningAuthor 5 of 5EMNLP Findings 2022 · 9 citations
- Narrate Dialogues for Better SummarizationAuthor 3 of 3EMNLP Findings 2022 · 5 citations
- ParaTag: A Dataset of Paraphrase Tagging for Fine-Grained Labels, NLG Evaluation, and Data AugmentationAuthor 5 of 5EMNLP 2022 · 3 citations
- Want To Reduce Labeling Cost? GPT-3 Can HelpAuthor 5 of 5EMNLP Findings 2021 · 177 citations
- Fusing Context Into Knowledge Graph for Commonsense Question AnsweringAuthor 5 of 6ACL Findings 2021 · 62 citations
- Retrieval Enhanced Model for Commonsense GenerationAuthor 7 of 7ACL Findings 2021 · 26 citations
- Few-shot Natural Language Generation for Task-Oriented DialogAuthor 6 of 7EMNLP Findings 2020 · 164 citations
- A Hierarchical Network for Abstractive Meeting Summarization with Cross-Domain PretrainingAuthor 3 of 4EMNLP Findings 2020 · 135 citations
- TED: A Pretrained Unsupervised Summarization Model with Theme Modeling and DenoisingAuthor 4 of 6EMNLP Findings 2020 · 49 citations
