Xiaoyan Zhu

Encoding Syntactic Knowledge in Neural Networks for Sentiment Classification

2017 · ACM Transactions on Information Systems

Phrase/Sentence representation is one of the most important problems in natural language processing. Many neural network models such as Convolutional Neural Network (CNN), Recursive Neural Network (RNN), and Long Short-Term Memory (LSTM) have been proposed …

Adaptive N-Gram Model Based Differentially Private Trajectory Synthesis Method

2019

With the development of data science and deep learning, people tend to share their data to boost the precision of the trained model. However, the data to be shared may contain a very large number …

On the Safety of Conversational Models: Taxonomy, Dataset, and Benchmark

2022 · Findings of the Association for Computational Linguistics: ACL 2022

Dialogue safety problems severely limit the real-world deployment of neural conversational models and have attracted great research interests recently. However, dialogue safety problems remain under-defined and the corresponding dataset is scarce. We propose a taxonomy …

Learning Tag Embeddings and Tag-specific Composition Functions in Recursive Neural Network

2015

Qiao Qian, Bo Tian, Minlie Huang, Yang Liu, Xuan Zhu, Xiaoyan Zhu. Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume …

Emotional Chatting Machine: Emotional Conversation Generation with Internal and External Memory

2017 · arXiv (Cornell University)

Perception and expression of emotion are key factors to the success of dialogue systems or conversational agents. However, this problem has not been studied in large-scale conversation generation so far. In this paper, we propose …

Reinforcement Learning for Relation Classification from Noisy Data

2018 · arXiv (Cornell University)

Existing relation classification methods that rely on distant supervision assume that a bag of sentences mentioning an entity pair are all describing a relation for the entity pair. Such methods, performing classification at the bag …

Commonsense Knowledge Aware Conversation Generation with Graph Attention

2018

Commonsense knowledge is vital to many natural language processing tasks. In this paper, we present a novel open-domain conversation generation model to demonstrate how large-scale commonsense knowledge can facilitate language understanding and generation. Given a …

Papers by this author

Encoding Syntactic Knowledge in Neural Networks for Sentiment Classification

Adaptive N-Gram Model Based Differentially Private Trajectory Synthesis Method

On the Safety of Conversational Models: Taxonomy, Dataset, and Benchmark

Learning Tag Embeddings and Tag-specific Composition Functions in Recursive Neural Network

Emotional Chatting Machine: Emotional Conversation Generation with Internal and External Memory

Reinforcement Learning for Relation Classification from Noisy Data

Commonsense Knowledge Aware Conversation Generation with Graph Attention

Emotional Chatting Machine: Emotional Conversation Generation with Internal and External Memory

Long and Diverse Text Generation with Planning-based Hierarchical Variational Model

A Knowledge-Enhanced Pretraining Model for Commonsense Story Generation

SentiLARE: Sentiment-Aware Language Representation Learning with Linguistic Knowledge