Search Results for author: Bai Li

Found 20 papers, 7 papers with code

What do writing features tell us about AI papers?

1 code implementation13 Jul 2021 Zining Zhu, Bai Li, Yang Xu, Frank Rudzicz

As the numbers of submissions to conferences grow quickly, the task of assessing the quality of academic papers automatically, convincingly, and with high accuracy attracts increasing attention.

How is BERT surprised? Layerwise detection of linguistic anomalies

1 code implementation ACL 2021 Bai Li, Zining Zhu, Guillaume Thomas, Yang Xu, Frank Rudzicz

Transformer language models have shown remarkable ability in detecting when a word is anomalous in context, but likelihood scores offer no information about the cause of the anomaly.

Density Estimation

TorontoCL at CMCL 2021 Shared Task: RoBERTa with Multi-Stage Fine-Tuning for Eye-Tracking Prediction

1 code implementation15 Apr 2021 Bai Li, Frank Rudzicz

In this paper, we describe our submission to the CMCL 2021 shared task on predicting human reading patterns.

Eye Tracking

Evolution of Part-of-Speech in Classical Chinese

no code implementations23 Sep 2020 Bai Li

Classical Chinese is a language notable for its word class flexibility: the same word may often be used as a noun or a verb.

Word class flexibility: A deep contextualized approach

2 code implementations EMNLP 2020 Bai Li, Guillaume Thomas, Yang Xu, Frank Rudzicz

Word class flexibility refers to the phenomenon whereby a single word form is used across different grammatical categories.

Word Embeddings

Towards Understanding Fast Adversarial Training

no code implementations4 Jun 2020 Bai Li, Shiqi Wang, Suman Jana, Lawrence Carin

Current neural-network-based classifiers are susceptible to adversarial examples.

Towards Practical Lottery Ticket Hypothesis for Adversarial Training

1 code implementation6 Mar 2020 Bai Li, Shiqi Wang, Yunhan Jia, Yantao Lu, Zhenyu Zhong, Lawrence Carin, Suman Jana

Recent research has proposed the lottery ticket hypothesis, suggesting that for a deep neural network, there exist trainable sub-networks performing equally or better than the original model with commensurate training steps.

Enhancing Cross-task Black-Box Transferability of Adversarial Examples with Dispersion Reduction

2 code implementations CVPR 2020 Yantao Lu, Yunhan Jia, Jian-Yu Wang, Bai Li, Weiheng Chai, Lawrence Carin, Senem Velipasalar

Neural networks are known to be vulnerable to carefully crafted adversarial examples, and these malicious samples often transfer, i. e., they remain adversarial even against other models.

Adversarial Attack Image Classification +2

Graph-Driven Generative Models for Heterogeneous Multi-Task Learning

no code implementations20 Nov 2019 Wenlin Wang, Hongteng Xu, Zhe Gan, Bai Li, Guoyin Wang, Liqun Chen, Qian Yang, Wenqi Wang, Lawrence Carin

We propose a novel graph-driven generative model, that unifies multiple heterogeneous learning tasks into the same framework.

Multi-Task Learning Type prediction

Representation Learning for Discovering Phonemic Tone Contours

no code implementations WS 2020 Bai Li, Jing Yi Xie, Frank Rudzicz

Tone is a prosodic feature used to distinguish words in many languages, some of which are endangered and scarcely documented.

Unsupervised Representation Learning

Real-world Conversational AI for Hotel Bookings

no code implementations27 Aug 2019 Bai Li, Nanyi Jiang, Joey Sham, Henry Shi, Hussein Fazal

In this paper, we present a real-world conversational AI system to search for and book hotels through text messaging.

Chatbot Dialogue Management +4

Multilingual prediction of Alzheimer's disease through domain adaptation and concept-based language modelling

no code implementations NAACL 2019 Kathleen C. Fraser, Nicklas Linz, Bai Li, Kristina Lundholm Fors, Frank Rudzicz, Alex K{\"o}nig, ra, Alex, Jan ersson, Philippe Robert, Dimitrios Kokkinakis

There is growing evidence that changes in speech and language may be early markers of dementia, but much of the previous NLP work in this area has been limited by the size of the available datasets.

Domain Adaptation Language Modelling

On Norm-Agnostic Robustness of Adversarial Training

no code implementations15 May 2019 Bai Li, Changyou Chen, Wenlin Wang, Lawrence Carin

Adversarial examples are carefully perturbed in-puts for fooling machine learning models.

Second-Order Adversarial Attack and Certifiable Robustness

no code implementations ICLR 2019 Bai Li, Changyou Chen, Wenlin Wang, Lawrence Carin

In this paper, we propose a powerful second-order attack method that reduces the accuracy of the defense model by Madry et al. (2017).

Adversarial Attack

Detecting dementia in Mandarin Chinese using transfer learning from a parallel corpus

no code implementations NAACL 2019 Bai Li, Yi-Te Hsu, Frank Rudzicz

Machine learning has shown promise for automatic detection of Alzheimer's disease (AD) through speech; however, efforts are hampered by a scarcity of data, especially in languages other than English.

Machine Translation Transfer Learning +1

Certified Adversarial Robustness with Additive Noise

2 code implementations NeurIPS 2019 Bai Li, Changyou Chen, Wenlin Wang, Lawrence Carin

The existence of adversarial data examples has drawn significant attention in the deep-learning community; such data are seemingly minimally perturbed relative to the original data, but lead to very different outputs from a deep-learning algorithm.

Adversarial Attack

Dropout during inference as a model for neurological degeneration in an image captioning network

no code implementations11 Aug 2018 Bai Li, Ran Zhang, Frank Rudzicz

We replicate a variation of the image captioning architecture by Vinyals et al. (2015), then introduce dropout during inference mode to simulate the effects of neurodegenerative diseases like Alzheimer's disease (AD) and Wernicke's aphasia (WA).

Image Captioning

A Unified Particle-Optimization Framework for Scalable Bayesian Sampling

no code implementations29 May 2018 Changyou Chen, Ruiyi Zhang, Wenlin Wang, Bai Li, Liqun Chen

There has been recent interest in developing scalable Bayesian sampling methods such as stochastic gradient MCMC (SG-MCMC) and Stein variational gradient descent (SVGD) for big-data analysis.

On Connecting Stochastic Gradient MCMC and Differential Privacy

no code implementations25 Dec 2017 Bai Li, Changyou Chen, Hao liu, Lawrence Carin

Significant success has been realized recently on applying machine learning to real-world applications.

Cannot find the paper you are looking for? You can Submit a new open access paper.