Search Results for author: Zhi-Hong Deng

Found 23 papers, 10 papers with code

Cross-Domain Few-Shot Classification via Adversarial Task Augmentation

1 code implementation29 Apr 2021 Haoqing Wang, Zhi-Hong Deng

However, when there exists the domain shift between the training tasks and the test tasks, the obtained inductive bias fails to generalize across domains, which degrades the performance of the meta-learning models.

Classification Cross-Domain Few-Shot +3

BCFNet: A Balanced Collaborative Filtering Network with Attention Mechanism

1 code implementation10 Mar 2021 Zi-Yuan Hu, Jin Huang, Zhi-Hong Deng, Chang-Dong Wang, Ling Huang, Jian-Huang Lai, Philip S. Yu

Representation learning tries to learn a common low dimensional space for the representations of users and items.

Representation Learning

Few-shot Learning with LSSVM Base Learner and Transductive Modules

1 code implementation12 Sep 2020 Haoqing Wang, Zhi-Hong Deng

The performance of meta-learning approaches for few-shot learning generally depends on three aspects: features suitable for comparison, the classifier ( base learner ) suitable for low-data scenarios, and valuable information from the samples to classify.

Few-Shot Learning

Self-Supervised Learning Aided Class-Incremental Lifelong Learning

no code implementations10 Jun 2020 Song Zhang, Gehui Shen, Jinsong Huang, Zhi-Hong Deng

Lifelong or continual learning remains to be a challenge for artificial neural network, as it is required to be both stable for preservation of old knowledge and plastic for acquisition of new knowledge.

class-incremental learning Incremental Learning +1

Generative Feature Replay with Orthogonal Weight Modification for Continual Learning

no code implementations7 May 2020 Gehui Shen, Song Zhang, Xiang Chen, Zhi-Hong Deng

For this scenario, generative replay is a promising strategy which generates and replays pseudo data for previous tasks to alleviate catastrophic forgetting.

class-incremental learning Incremental Learning

Fast Structured Decoding for Sequence Models

1 code implementation NeurIPS 2019 Zhiqing Sun, Zhuohan Li, Haoqing Wang, Zi Lin, Di He, Zhi-Hong Deng

However, these models assume that the decoding process of each token is conditionally independent of others.

Machine Translation

Neural Consciousness Flow

1 code implementation30 May 2019 Xiaoran Xu, Wei Feng, Zhiqing Sun, Zhi-Hong Deng

Instead, inspired by the consciousness prior proposed by Yoshua Bengio, we explore reasoning with the notion of attentive awareness from a cognitive perspective, and formulate it in the form of attentive message passing on graphs, called neural consciousness flow (NeuCFlow).

Decision Making Knowledge Base Completion

Leap-LSTM: Enhancing Long Short-Term Memory for Text Categorization

1 code implementation28 May 2019 Ting Huang, Gehui Shen, Zhi-Hong Deng

Compared to previous models which can also skip words, our model achieves better trade-offs between performance and efficiency.

General Classification Machine Translation +4

DivGraphPointer: A Graph Pointer Network for Extracting Diverse Keyphrases

no code implementations19 May 2019 Zhiqing Sun, Jian Tang, Pan Du, Zhi-Hong Deng, Jian-Yun Nie

Furthermore, we propose a diversified point network to generate a set of diverse keyphrases out of the word graph in the decoding process.

Document-level Document Summarization +2

DeepCF: A Unified Framework of Representation Learning and Matching Function Learning in Recommender System

2 code implementations15 Jan 2019 Zhi-Hong Deng, Ling Huang, Chang-Dong Wang, Jian-Huang Lai, Philip S. Yu

To solve this problem, many methods have been studied, which can be generally categorized into two types, i. e., representation learning-based CF methods and matching function learning-based CF methods.

Recommendation Systems Representation Learning

Unsupervised Neural Word Segmentation for Chinese via Segmental Language Modeling

1 code implementation EMNLP 2018 Zhiqing Sun, Zhi-Hong Deng

As far as we know, we are the first to propose a neural model for unsupervised CWS and achieve competitive performance to the state-of-the-art statistical models on four different datasets from SIGHAN 2005 bakeoff.

Chinese Word Segmentation Language Modelling

Learning to Compose over Tree Structures via POS Tags

no code implementations18 Aug 2018 Gehui Shen, Zhi-Hong Deng, Ting Huang, Xi Chen

Recursive Neural Network (RecNN), a type of models which compose words or phrases recursively over syntactic tree structures, has been proven to have superior ability to obtain sentence representation for a variety of NLP tasks.

POS Semantic Composition +1

MEMD: A Diversity-Promoting Learning Framework for Short-Text Conversation

no code implementations COLING 2018 Meng Zou, Xihan Li, Haokun Liu, Zhi-Hong Deng

Neural encoder-decoder models have been widely applied to conversational response generation, which is a research hot spot in recent years.

Conversational Response Generation Short-Text Conversation

A Novel Framework for Recurrent Neural Networks with Enhancing Information Processing and Transmission between Units

no code implementations2 Jun 2018 Xi Chen, Zhi-Hong Deng, Gehui Shen, Ting Huang

This paper proposes a novel framework for recurrent neural networks (RNNs) inspired by the human memory models in the field of cognitive neuroscience to enhance information processing and transmission between adjacent RNNs' units.

General Classification Image Classification +2

A Gap-Based Framework for Chinese Word Segmentation via Very Deep Convolutional Networks

no code implementations27 Dec 2017 Zhiqing Sun, Gehui Shen, Zhi-Hong Deng

However, if we consider segmenting a given sentence, the most intuitive idea is to predict whether to segment for each gap between two consecutive characters, which in comparison makes previous approaches seem too complex.

Chinese Word Segmentation

An Unsupervised Multi-Document Summarization Framework Based on Neural Document Model

no code implementations COLING 2016 Shulei Ma, Zhi-Hong Deng, Yunlun Yang

In the age of information exploding, multi-document summarization is attracting particular attention for the ability to help people get the main ideas in a short time.

Document-level Document Summarization +2

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