Portfolio item number 1
Short description of portfolio item number 1
Posts by Collection
portfolio
Portfolio item number 2
Short description of portfolio item number 2
publications
A Unified Neural Coherence Model
Published in Journal 1, 2009
This paper is about the number 1. The number 2 is left for future work.
Recommended citation: Your Name, You. (2009). "Paper Title Number 1." Journal 1. 1(1).
Paper Title Number 2
Published in Journal 1, 2010
This paper is about the number 2. The number 3 is left for future work.
Recommended citation: Your Name, You. (2010). "Paper Title Number 2." Journal 1. 1(2). http://academicpages.github.io/files/paper2.pdf
Paper Title Number 3
Published in Journal 1, 2015
This paper is about the number 3. The number 4 is left for future work.
Recommended citation: Your Name, You. (2015). "Paper Title Number 3." Journal 1. 1(3). http://academicpages.github.io/files/paper3.pdf
talks
A Unified Neural Coherence Model
Published:
Recently, neural approaches to coherence modeling have achieved state-of-the-art results in several evaluation tasks. However, we show that most of these models often fail on harder tasks with more realistic application scenarios. In particular, the existing models underperform on tasks that require the model to be sensitive to local contexts such as candidate ranking in conversational dialogue and in machine translation. In this paper, we propose a unified coherence model that incorporates sentence grammar, inter-sentence coherence relations, and global coherence patterns into a common neural framework. With extensive experiments on local and global discrimination tasks, we demonstrate that our proposed model outperforms existing models by a good margin, and establish a new state-of-the-art.
Neural Text Generation with Unlikelihood Training
Published:
A tutorial talk for Neural Text Generation with Unlikelihood Training (ICLR 2020)
SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient
Published:
A tutorial talk for SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient (AAAI 2017)
Text Generation by Learning from Off-Policy Demonstrations
Published:
A tutorial talk for Text Generation by Learning from Off-Policy Demonstrations (ICLR 2021)
GradMask: Gradient-Guided Token Masking for Textual Adversarial Example Detection
Published:
We present GradMask, a simple adversarial example detection scheme for natural language processing (NLP) models. It uses gradient signals to detect adversarially perturbed tokens in an input sequence and occludes such tokens by a masking process. GradMask provides several advantages over existing methods including improved detection performance and an interpretation of its decision with a only moderate computational cost. Its approximated inference cost is no more than a single forward- and back-propagation through the target model without requiring any additional detection module. Extensive evaluation on widely adopted NLP benchmark datasets demonstrates the efficiency and effectiveness of GradMask.
teaching
DeepNLP
Graduate course, University 1, Department, 2014
This is a description of a teaching experience. You can use markdown like any other post.
Teaching experience 2
Workshop, University 1, Department, 2015
This is a description of a teaching experience. You can use markdown like any other post.