49 citations · 101 across the 18 of their papers we have counts for
7 papers · 1 filter
An Investigation of Potential Function Designs for Neural CRF
Zechuan Hu, Yong Jiang, Nguyen Bach +4
The neural linear-chain CRF model is one of the most widely-used approach to sequence labeling. In this paper, we investigate a series of increasingly expressive potential function…
Neural Latent Dependency Model for Sequence Labeling
Yang Zhou, Yong Jiang, Zechuan Hu +1
Sequence labeling is a fundamental problem in machine learning, natural language processing and many other fields. A classic approach to sequence labeling is linear chain condition…
Adversarial Attack and Defense of Structured Prediction Models
Wenjuan Han, Liwen Zhang, Yong Jiang +1
Building an effective adversarial attacker and elaborating on countermeasures for adversarial attacks for natural language processing (NLP) have attracted a lot of research in rece…
AIN: Fast and Accurate Sequence Labeling with Approximate Inference Network
Xinyu Wang, Yong Jiang, Nguyen Bach +4
The linear-chain Conditional Random Field (CRF) model is one of the most widely-used neural sequence labeling approaches. Exact probabilistic inference algorithms such as the forwa…
A Survey of Unsupervised Dependency Parsing
Wenjuan Han, Yong Jiang, Hwee Tou Ng +1
Syntactic dependency parsing is an important task in natural language processing. Unsupervised dependency parsing aims to learn a dependency parser from sentences that have no anno…
More Embeddings, Better Sequence Labelers?
Xinyu Wang, Yong Jiang, Nguyen Bach +4
Recent work proposes a family of contextual embeddings that significantly improves the accuracy of sequence labelers over non-contextual embeddings. However, there is no definite c…
Enhanced Universal Dependency Parsing with Second-Order Inference and Mixture of Training Data
Xinyu Wang, Yong Jiang, Kewei Tu
This paper presents the system used in our submission to the \textit{IWPT 2020 Shared Task}. Our system is a graph-based parser with second-order inference. For the low-resource Ta…