Xuanjing Huang

is this you? claim profile

Professor of Computer Science at Iowa State University since 2001, Scientist at Paracel from 1999-2001, Doctor of Philosophy (Ph.D.) Field Of StudyComputer Science at Penn State University from1985-1990.

Generating Adversarial Examples in Chinese Texts Using Sentence-Pieces

Adversarial attacks in texts are mostly substitution-based methods that ...
12/29/2020 ∙ by Linyang Li, et al. ∙ 0 ∙ share

read it
Uncertainty-Aware Label Refinement for Sequence Labeling

Conditional random fields (CRF) for label decoding has become ubiquitous...
12/19/2020 ∙ by Tao Gui, et al. ∙ 0 ∙ share

read it
Topic-Oriented Spoken Dialogue Summarization for Customer Service with Saliency-Aware Topic Modeling

In a customer service system, dialogue summarization can boost service e...
12/14/2020 ∙ by Yicheng Zou, et al. ∙ 0 ∙ share

read it
Unsupervised Summarization for Chat Logs with Topic-Oriented Ranking and Context-Aware Auto-Encoders

Automatic chat summarization can help people quickly grasp important inf...
12/14/2020 ∙ by Yicheng Zou, et al. ∙ 0 ∙ share

read it
SenSeNet: Neural Keyphrase Generation with Document Structure

Keyphrase Generation (KG) is the task of generating central topics from ...
12/12/2020 ∙ by Yichao Luo, et al. ∙ 0 ∙ share

read it
An Enhanced Knowledge Injection Model for Commonsense Generation

Commonsense generation aims at generating plausible everyday scenario de...
12/01/2020 ∙ by Zhihao Fan, et al. ∙ 0 ∙ share

read it
Generating universal language adversarial examples by understanding and enhancing the transferability across neural models

Deep neural network models are vulnerable to adversarial attacks. In man...
11/17/2020 ∙ by Liping Yuan, et al. ∙ 11 ∙ share

read it
Text Information Aggregation with Centrality Attention

A lot of natural language processing problems need to encode the text se...
11/16/2020 ∙ by Jingjing Gong, et al. ∙ 0 ∙ share

read it
RethinkCWS: Is Chinese Word Segmentation a Solved Task?

The performance of the Chinese Word Segmentation (CWS) systems has gradu...
11/13/2020 ∙ by Jinlan Fu, et al. ∙ 0 ∙ share

read it
CDEvalSumm: An Empirical Study of Cross-Dataset Evaluation for Neural Summarization Systems

Neural network-based models augmented with unsupervised pre-trained know...
10/11/2020 ∙ by Yiran Chen, et al. ∙ 0 ∙ share

read it
CoLAKE: Contextualized Language and Knowledge Embedding

With the emerging branch of incorporating factual knowledge into pre-tra...
10/01/2020 ∙ by Tianxiang Sun, et al. ∙ 21 ∙ share

read it
fastHan: A BERT-based Joint Many-Task Toolkit for Chinese NLP

We present fastHan, an open-source toolkit for four basic tasks in Chine...
09/18/2020 ∙ by Zhichao Geng, et al. ∙ 0 ∙ share

read it
Tasty Burgers, Soggy Fries: Probing Aspect Robustness in Aspect-Based Sentiment Analysis

Aspect-based sentiment analysis (ABSA) aims to predict the sentiment tow...
09/16/2020 ∙ by Xiaoyu Xing, et al. ∙ 0 ∙ share

read it
Defense against Adversarial Attacks in NLP via Dirichlet Neighborhood Ensemble

Despite neural networks have achieved prominent performance on many natu...
06/20/2020 ∙ by Yi Zhou, et al. ∙ 0 ∙ share

read it
Task-oriented Dialogue System for Automatic Disease Diagnosis via Hierarchical Reinforcement Learning

In this paper, we focus on automatic disease diagnosis with reinforcemen...
04/29/2020 ∙ by Kangenbei Liao, et al. ∙ 0 ∙ share

read it
Leveraging Declarative Knowledge in Text and First-Order Logic for Fine-Grained Propaganda Detection

We study the detection of propagandistic text fragments in news articles...
04/29/2020 ∙ by Ruize Wang, et al. ∙ 7 ∙ share

read it
Heterogeneous Graph Neural Networks for Extractive Document Summarization

As a crucial step in extractive document summarization, learning cross-s...
04/26/2020 ∙ by Danqing Wang, et al. ∙ 0 ∙ share

read it
FLAT: Chinese NER Using Flat-Lattice Transformer

Recently, the character-word lattice structure has been proved to be eff...
04/24/2020 ∙ by Xiaonan Li, et al. ∙ 0 ∙ share

read it
Extractive Summarization as Text Matching

This paper creates a paradigm shift with regard to the way we build neur...
04/19/2020 ∙ by Ming Zhong, et al. ∙ 0 ∙ share

read it
Unified Multi-Criteria Chinese Word Segmentation with BERT

Multi-Criteria Chinese Word Segmentation (MCCWS) aims at finding word bo...
04/13/2020 ∙ by Zhen Ke, et al. ∙ 0 ∙ share

read it
Pre-trained Models for Natural Language Processing: A Survey

Recently, the emergence of pre-trained models (PTMs) has brought natural...
03/18/2020 ∙ by Xipeng Qiu, et al. ∙ 0 ∙ share

read it
Improving BERT Fine-Tuning via Self-Ensemble and Self-Distillation

Fine-tuning pre-trained language models like BERT has become an effectiv...
02/24/2020 ∙ by Yige Xu, et al. ∙ 0 ∙ share

read it
K-Adapter: Infusing Knowledge into Pre-Trained Models with Adapters

We study the problem of injecting knowledge into large pre-trained model...
02/05/2020 ∙ by Ruize Wang, et al. ∙ 0 ∙ share

read it
Rethinking Generalization of Neural Models: A Named Entity Recognition Case Study

While neural network-based models have achieved impressive performance o...
01/12/2020 ∙ by Jinlan Fu, et al. ∙ 0 ∙ share

read it
Chinese Named Entity Recognition Augmented with Lexicon Memory

Inspired by a concept of content-addressable retrieval from cognitive sc...
12/17/2019 ∙ by Yi Zhou, et al. ∙ 0 ∙ share

read it
Constructing Multiple Tasks for Augmentation: Improving Neural Image Classification With K-means Features

Multi-task learning (MTL) has received considerable attention, and numer...
11/18/2019 ∙ by Tao Gui, et al. ∙ 0 ∙ share

read it
Learning Sparse Sharing Architectures for Multiple Tasks

Most existing deep multi-task learning models are based on parameter sha...
11/12/2019 ∙ by Tianxiang Sun, et al. ∙ 0 ∙ share

read it
Keep it Consistent: Topic-Aware Storytelling from an Image Stream via Iterative Multi-agent Communication

Visual storytelling aims to generate a narrative paragraph from a sequen...
11/11/2019 ∙ by Ruize Wang, et al. ∙ 20 ∙ share

read it
Discrete Argument Representation Learning for Interactive Argument Pair Identification

In this paper, we focus on extracting interactive argument pairs from tw...
11/05/2019 ∙ by Lu Ji, et al. ∙ 0 ∙ share

read it
A Closer Look at Data Bias in Neural Extractive Summarization Models

In this paper, we take stock of the current state of summarization datas...
09/30/2019 ∙ by Ming Zhong, et al. ∙ 0 ∙ share

read it
Weighed Domain-Invariant Representation Learning for Cross-domain Sentiment Analysis

Cross-domain sentiment analysis is currently a hot topic in the research...
09/18/2019 ∙ by Minlong Peng, et al. ∙ 0 ∙ share

read it
Exploring Domain Shift in Extractive Text Summarization

Although domain shift has been well explored in many NLP applications, i...
08/30/2019 ∙ by Danqing Wang, et al. ∙ 0 ∙ share

read it
GlossBERT: BERT for Word Sense Disambiguation with Gloss Knowledge

Word Sense Disambiguation (WSD) aims to find the exact sense of an ambig...
08/20/2019 ∙ by Luyao Huang, et al. ∙ 0 ∙ share

read it
Simplify the Usage of Lexicon in Chinese NER

Recently, many works have tried to utilizing word lexicon to augment the...
08/16/2019 ∙ by Minlong Peng, et al. ∙ 0 ∙ share

read it
DropAttention: A Regularization Method for Fully-Connected Self-Attention Networks

Variants dropout methods have been designed for the fully-connected laye...
07/25/2019 ∙ by Lin Zehui, et al. ∙ 0 ∙ share

read it
Searching for Effective Neural Extractive Summarization: What Works and What's Next

The recent years have seen remarkable success in the use of deep neural ...
07/08/2019 ∙ by Ming Zhong, et al. ∙ 0 ∙ share

read it
Multi-Criteria Chinese Word Segmentation with Transformer

Different linguistic perspectives cause many diverse segmentation criter...
06/28/2019 ∙ by Xipeng Qiu, et al. ∙ 0 ∙ share

read it
Distantly Supervised Named Entity Recognition using Positive-Unlabeled Learning

In this work, we explore the way to perform named entity recognition (NE...
06/04/2019 ∙ by Minlong Peng, et al. ∙ 0 ∙ share

read it
Learning Task-specific Representation for Novel Words in Sequence Labeling

Word representation is a key component in neural-network-based sequence ...
05/29/2019 ∙ by Minlong Peng, et al. ∙ 0 ∙ share

read it
Style Transformer: Unpaired Text Style Transfer without Disentangled Latent Representation

Disentangling the content and style in the latent space is prevalent in ...
05/14/2019 ∙ by Ning Dai, et al. ∙ 0 ∙ share

read it
How to Fine-Tune BERT for Text Classification?

Language model pre-training has proven to be useful in learning universa...
05/14/2019 ∙ by Chi Sun, et al. ∙ 0 ∙ share

read it
A Unified Model for Joint Chinese Word Segmentation and Dependency Parsing

Chinese word segmentation and dependency parsing are two fundamental tas...
04/09/2019 ∙ by Hang Yan, et al. ∙ 0 ∙ share

read it
VCWE: Visual Character-Enhanced Word Embeddings

Chinese is a logographic writing system, and the shape of Chinese charac...
02/23/2019 ∙ by Chi Sun, et al. ∙ 0 ∙ share

read it
Contextualized Non-local Neural Networks for Sequence Learning

Recently, a large number of neural mechanisms and models have been propo...
11/21/2018 ∙ by Pengfei Liu, et al. ∙ 0 ∙ share

read it
Long Short-Term Memory with Dynamic Skip Connections

In recent years, long short-term memory (LSTM) has been successfully use...
11/09/2018 ∙ by Tao Gui, et al. ∙ 0 ∙ share

read it
Meta-Learning Multi-task Communication

In this paper, we describe a general framework: Parameters Read-Write Ne...
10/23/2018 ∙ by Pengfei Liu, et al. ∙ 0 ∙ share

read it
Deformable Stacked Structure for Named Entity Recognition

Neural architecture for named entity recognition has achieved great succ...
09/24/2018 ∙ by Shuyang Cao, et al. ∙ 0 ∙ share

read it
Exploring Shared Structures and Hierarchies for Multiple NLP Tasks

Designing shared neural architecture plays an important role in multi-ta...
08/23/2018 ∙ by Junkun Chen, et al. ∙ 0 ∙ share

read it
Gaussian Word Embedding with a Wasserstein Distance Loss

Comparing with word embedding that based on the point representation, di...
08/21/2018 ∙ by Chi Sun, et al. ∙ 0 ∙ share

read it
Information Aggregation via Dynamic Routing for Sequence Encoding

While much progress has been made in how to encode a text sequence into ...
06/05/2018 ∙ by Jingjing Gong, et al. ∙ 0 ∙ share

read it

Xuanjing Huang

Featured Co-authors