Eric P. Xing

Data-to-Text Generation with Style Imitation

2019 · arXiv (Cornell University)

Recent neural approaches to data-to-text generation have mostly focused on improving content fidelity while lacking explicit control over writing styles (e.g., word choices, sentence structures). More traditional systems use templates to determine the realization of …

Federated Learning via Posterior Averaging: A New Perspective and Practical Algorithms

2020 · arXiv (Cornell University)

Federated learning is typically approached as an optimization problem, where the goal is to minimize a global loss function by distributing computation across client devices that possess local data and specify different parts of the …

Summarizing Text on Any Aspects: A Knowledge-Informed Weakly-Supervised Approach

2020

Given a document and a target aspect (e.g., a topic of interest), aspect-based abstractive summarization attempts to generate a summary with respect to the aspect. Previous studies usually assume a small pre-defined set of aspects …

Progressive Generation of Long Text with Pretrained Language Models

2021

Bowen Tan, Zichao Yang, Maruan Al-Shedivat, Eric Xing, Zhiting Hu. Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2021.

NOTMAD: Estimating Bayesian Networks with Sample-Specific Structures and Parameters

2021 · arXiv (Cornell University)

Context-specific Bayesian networks (i.e. directed acyclic graphs, DAGs) identify context-dependent relationships between variables, but the non-convexity induced by the acyclicity requirement makes it difficult to share information between context-specific estimators (e.g. with graph generator functions). …

On the Generation of Medical Dialogues for COVID19

2020

<div>Under the pandemic of COVID-19, people experiencing COVID19-related symptoms or exposed to risk factors have a pressing need to consult doctors. Due to hospital closure,</div><div>a lot of consulting services have been moved online. Because of …

Memory-adaptive Depth-wise Heterogeneous Federated Learning

2023 · arXiv (Cornell University)

Federated learning is a promising paradigm that allows multiple clients to collaboratively train a model without sharing the local data. However, the presence of heterogeneous devices in federated learning, such as mobile phones and IoT …

One-for-All: Generalized LoRA for Parameter-Efficient Fine-tuning

2023 · arXiv (Cornell University)

We present Generalized LoRA (GLoRA), an advanced approach for universal parameter-efficient fine-tuning tasks. Enhancing Low-Rank Adaptation (LoRA), GLoRA employs a generalized prompt module to optimize pre-trained model weights and adjust intermediate activations, providing more flexibility …

Incorporating Word Correlation Knowledge into Topic Modeling

2015

This paper studies how to incorporate the external word correlation knowledge to improve the coherence of topic modeling. Existing topic models assume words are generated independently and lack the mechanism to utilize the rich similarity …

Harnessing Deep Neural Networks with Logic Rules

2016 · arXiv (Cornell University)

Combining deep neural networks with structured logic rules is desirable to harness flexibility and reduce uninterpretability of the neural models. We propose a general framework capable of enhancing various types of neural networks (e.g., CNNs …