Searcharxiv⌕ Search

arXiv subjects

Lidan Wang

Publications and source records attributed to Lidan Wang.

26 records · Page 2Linked to original sources
arXiv2020

Understanding Points of Correspondence between Sentences for Abstractive Summarization

Fusing sentences containing disparate content is a remarkable human ability that helps create informative and succinct summaries. Such a simple task for humans has remained challenging for modern abstractive summarizers, substantially restricting their applicability in real-world scenarios. In this paper, we present an investigation into fusing sentences drawn from a document by introducing the notion of points of correspondence, which are cohesive devices that tie any two sentences together into a coherent text. The types of points of correspondence are delineated by text cohesion theory, covering pronominal and nominal referencing, repetition and beyond. We create a dataset containing the documents, source and fusion sentences, and human annotations of points of correspondence between sentences. Our dataset bridges the gap between coreference resolution and summarization. It is publicly shared to serve as a basis for future work to measure the success of sentence fusion systems. (https://github.com/ucfnlp/points-of-correspondence)

cs.CL↗
arXiv2020

Exponential stability of 3D stochastic primitive equations driven by fractional noise

In this article, we study the stability of solutions to 3D stochastic primitive equations driven by fractional noise. Since the fractional Brownian motion is essentially different from Brownian motion, lots of stochastic analysis tools are not available to study the exponential stability for the stochastic systems. Therefore, apart from the standard method for the case of Brownian motion, we develop a new method to show that 3D stochastic primitive equations driven by fractional noise converge almost surely exponentially to the stationary solutions. This method may be applied to other stochastic hydrodynamic equations and other noises including Brownian motion and Lévy noise.

math.PR↗
arXiv2019

Global well-posedness of stochastic nematic liquid crystals with random initial and random boundary conditions driven by multiplicative noise

The flow of nematic liquid crystals can be described by a highly nonlinear stochastic hydrodynamical model, thus is often influenced by random fluctuations, such as uncertainty in specifying initial conditions and boundary conditions. In this article, we consider the $2$-D stochastic nematic liquid crystals with the velocity field perturbed by affine-linear multiplicative white noise, with random initial data and random boundary conditions. Our main objective is to establish the global well-posedness of the stochastic equations under certain sufficient Malliavin regularity of the initial conditions and the boundary conditions. The Malliavin calculus techniques play important roles in proving the global existence of the solutions to the stochastic nematic liquid crystal models with random initial and random boundary conditions. It should be pointed out that the global well-posedness is also true when the stochastic system is perturbed by the noise on the boundary.

math.PR↗
arXiv2018

High-Quality Facial Photo-Sketch Synthesis Using Multi-Adversarial Networks

Synthesizing face sketches from real photos and its inverse have many applications. However, photo/sketch synthesis remains a challenging problem due to the fact that photo and sketch have different characteristics. In this work, we consider this task as an image-to-image translation problem and explore the recently popular generative models (GANs) to generate high-quality realistic photos from sketches and sketches from photos. Recent GAN-based methods have shown promising results on image-to-image translation problems and photo-to-sketch synthesis in particular, however, they are known to have limited abilities in generating high-resolution realistic images. To this end, we propose a novel synthesis framework called Photo-Sketch Synthesis using Multi-Adversarial Networks, (PS2-MAN) that iteratively generates low resolution to high resolution images in an adversarial way. The hidden layers of the generator are supervised to first generate lower resolution images followed by implicit refinement in the network to generate higher resolution images. Furthermore, since photo-sketch synthesis is a coupled/paired translation problem, we leverage the pair information using CycleGAN framework. Both Image Quality Assessment (IQA) and Photo-Sketch Matching experiments are conducted to demonstrate the superior performance of our framework in comparison to existing state-of-the-art solutions. Code available at: https://github.com/lidan1/PhotoSketchMAN.

cs.CV↗
arXiv2015

Applying Deep Learning to Answer Selection: A Study and An Open Task

We apply a general deep learning framework to address the non-factoid question answering task. Our approach does not rely on any linguistic tools and can be applied to different languages or domains. Various architectures are presented and compared. We create and release a QA corpus and setup a new QA task in the insurance domain. Experimental results demonstrate superior performance compared to the baseline methods and various technologies give further improvements. For this highly challenging task, the top-1 accuracy can reach up to 65.3% on a test set, which indicates a great potential for practical use.

cs.CL↗