“Wanyu Du”的用户个人学术档案
 | Wanyu DuUniversity of Virginia 在 virginia.edu 的电子邮件经过验证 被引用次数：379 |
The gem benchmark: Natural language generation, its evaluation and metrics
We introduce GEM, a living benchmark for natural language Generation (NLG), its Evaluation,
and Metrics. Measuring progress in NLG relies on a constantly evolving ecosystem of …
and Metrics. Measuring progress in NLG relies on a constantly evolving ecosystem of …
Read, revise, repeat: A system demonstration for human-in-the-loop iterative text revision
Revision is an essential part of the human writing process. It tends to be strategic, adaptive,
and, more importantly, iterative in nature. Despite the success of large language models on …
and, more importantly, iterative in nature. Despite the success of large language models on …
Understanding iterative revision from human-written text
… Wanyu Du1∗, Vipul Raheja2 , Dhruv Kumar2 , Zae Myung Kim3 , Melissa Lopez2 , Dongyeop
Kang4 … * This research was performed when Wanyu Du was interning at Grammarly. …
Kang4 … * This research was performed when Wanyu Du was interning at Grammarly. …
Diverse text generation via variational encoder-decoder models with gaussian process priors
Generating high quality texts with high diversity is important for many NLG applications, but
current methods mostly focus on building deterministic models to generate higher quality …
current methods mostly focus on building deterministic models to generate higher quality …
Improving Iterative Text Revision by Learning Where to Edit from Other Revision Tasks
Iterative text revision improves text quality by fixing grammatical errors, rephrasing for better
readability or contextual appropriateness, or reorganizing sentence structures throughout a …
readability or contextual appropriateness, or reorganizing sentence structures throughout a …
An empirical comparison on imitation learning and reinforcement learning for paraphrase generation
Generating paraphrases from given sentences involves decoding words step by step from a
large vocabulary. To learn a decoder, supervised learning which maximizes the likelihood of …
large vocabulary. To learn a decoder, supervised learning which maximizes the likelihood of …
An effective optimization algorithm for application mapping in network-on-chip designs
The application mapping problem is an NP-hard combinatorial optimization problem in
network-on-chip (NoC) design. Applications of size (n > 30) cannot be solved optimally by an …
network-on-chip (NoC) design. Applications of size (n > 30) cannot be solved optimally by an …
An Electrostatic‐Induction‐Enabled Anti‐Touching Hydrogel Dressing for Chronic Wound Care
Chronic wounds are inherently vulnerable to external mechanical contact owing to their
impaired physiological states. Accidental touching may lead to secondary damage to delicate …
impaired physiological states. Accidental touching may lead to secondary damage to delicate …
Self-training with Two-phase Self-augmentation for Few-shot Dialogue Generation
In task-oriented dialogue systems, response generation from meaning representations (MRs)
often suffers from limited training examples, due to the high cost of annotating MR-to-Text …
often suffers from limited training examples, due to the high cost of annotating MR-to-Text …
[HTML][HTML] Epidemic and control of COVID-19 in Niger: quantitative analyses in a least developed country
…, ZW Li, JT Wei, RZ Ye, WJ Wang, WY Du… - Journal of global …, 2020 - ncbi.nlm.nih.gov
Background The COVID-19 pandemic is challenging the public health response system
worldwide, especially in poverty-stricken, war-torn, and least developed countries (LDCs). …
worldwide, especially in poverty-stricken, war-torn, and least developed countries (LDCs). …