Search Results for author: Feng Ji

Found 30 papers, 8 papers with code

Recovery of Graph Signals from Sign Measurements

no code implementations26 Sep 2021 Wenwei Liu, Hui Feng, Kaixuan Wang, Feng Ji, Bo Hu

Sampling and interpolation have been extensively studied, in order to reconstruct or estimate the entire graph signal from the signal values on a subset of vertexes, of which most achievements are about continuous signals.

KACE: Generating Knowledge Aware Contrastive Explanations for Natural Language Inference

1 code implementation ACL 2021 Qianglong Chen, Feng Ji, Xiangji Zeng, Feng-Lin Li, Ji Zhang, Haiqing Chen, Yin Zhang

In order to better understand the reason behind model behaviors (i. e., making predictions), most recent works have exploited generative models to provide complementary explanations.

Language Modelling Natural Language Inference

REPT: Bridging Language Models and Machine Reading Comprehension via Retrieval-Based Pre-training

1 code implementation10 May 2021 Fangkai Jiao, Yangyang Guo, Yilin Niu, Feng Ji, Feng-Lin Li, Liqiang Nie

Pre-trained Language Models (PLMs) have achieved great success on Machine Reading Comprehension (MRC) over the past few years.

Machine Reading Comprehension

AdaVQA: Overcoming Language Priors with Adapted Margin Cosine Loss

1 code implementation5 May 2021 Yangyang Guo, Liqiang Nie, Zhiyong Cheng, Feng Ji, Ji Zhang, Alberto del Bimbo

Experimental results demonstrate that our adapted margin cosine loss can greatly enhance the baseline models with an absolute performance gain of 15\% on average, strongly verifying the potential of tackling the language prior problem in VQA from the angle of the answer feature space learning.

Question Answering Visual Question Answering

Learning on heterogeneous graphs using high-order relations

no code implementations29 Mar 2021 See Hian Lee, Feng Ji, Wee Peng Tay

A heterogeneous graph consists of different vertices and edges types.

Signal processing with a distribution of graph operators

no code implementations11 Dec 2020 Feng Ji, Wee Peng Tay

In this paper, we develop a signal processing framework of a network without explicit knowledge of the network topology.

Learning to Expand: Reinforced Pseudo-relevance Feedback Selection for Information-seeking Conversations

no code implementations25 Nov 2020 Haojie Pan, Cen Chen, Minghui Qiu, Liu Yang, Feng Ji, Jun Huang, Haiqing Chen

More specifically, we proposed a reinforced selector to extract useful PRF terms to enhance response candidates and a BERT based response ranker to rank the PRF-enhanced responses.

Information Seeking

Improving Commonsense Question Answering by Graph-based Iterative Retrieval over Multiple Knowledge Sources

no code implementations COLING 2020 Qianglong Chen, Feng Ji, Haiqing Chen, Yin Zhang

More concretely, we first introduce a novel graph-based iterative knowledge retrieval module, which iteratively retrieves concepts and entities related to the given question and its choices from multiple knowledge sources.

Language Modelling Natural Language Understanding +1

Sampling Theory of Bandlimited Continuous-Time Graph Signals

no code implementations20 Oct 2020 Feng Ji, Hui Feng, Hang Sheng, Wee Peng Tay

A continuous-time graph signal can be viewed as a time series of graph signals.

Time Series

AliMe KG: Domain Knowledge Graph Construction and Application in E-commerce

no code implementations24 Sep 2020 Feng-Lin Li, Hehong Chen, Guohai Xu, Tian Qiu, Feng Ji, Ji Zhang, Haiqing Chen

Pre-sales customer service is of importance to E-commerce platforms as it contributes to optimizing customers' buying process.

graph construction Question Answering

Predict-then-Decide: A Predictive Approach for Wait or Answer Task in Dialogue Systems

no code implementations27 May 2020 Zehao Lin, Shaobo Cui, Guodun Li, Xiaoming Kang, Feng Ji, FengLin Li, Zhongzhou Zhao, Haiqing Chen, Yin Zhang

More specifically, we take advantage of a decision model to help the dialogue system decide whether to wait or answer.

MTSS: Learn from Multiple Domain Teachers and Become a Multi-domain Dialogue Expert

no code implementations21 May 2020 Shuke Peng, Feng Ji, Zehao Lin, Shaobo Cui, Haiqing Chen, Yin Zhang

How to build a high-quality multi-domain dialogue system is a challenging work due to its complicated and entangled dialogue state space among each domain, which seriously limits the quality of dialogue policy, and further affects the generated response.

Subgraph Signal Processing

no code implementations11 May 2020 Feng Ji, Wee Peng Tay, Giacomo Kahn

Graph signal processing, like the graph Fourier transform, requires the full graph signal at every vertex of the graph.

Signal processing on simplicial complexes

no code implementations6 Apr 2020 Feng Ji, Giacomo Kahn, Wee Peng Tay

In this paper, we develop a signal processing framework on simplicial complexes, such that we recover the traditional GSP theory when restricted to signals on graphs.

Task-Oriented Conversation Generation Using Heterogeneous Memory Networks

no code implementations IJCNLP 2019 Zehao Lin, Xinjing Huang, Feng Ji, Haiqing Chen, Ying Zhang

How to incorporate external knowledge into a neural dialogue model is critically important for dialogue systems to behave like real humans.

Review-Driven Answer Generation for Product-Related Questions in E-Commerce

1 code implementation27 Apr 2019 Shiqian Chen, Chenliang Li, Feng Ji, Wei Zhou, Haiqing Chen

Then, we devise a mechanism to identify the relevant information from the noise-prone review snippets and incorporate this information to guide the answer generation.

GFCN: A New Graph Convolutional Network Based on Parallel Flows

no code implementations25 Feb 2019 Feng Ji, Jielong Yang, Qiang Zhang, Wee Peng Tay

In view of the huge success of convolution neural networks (CNN) for image classification and object recognition, there have been attempts to generalize the method to general graph-structured data.

General Classification Image Classification +1

Learning to Selectively Transfer: Reinforced Transfer Learning for Deep Text Matching

no code implementations30 Dec 2018 Chen Qu, Feng Ji, Minghui Qiu, Liu Yang, Zhiyu Min, Haiqing Chen, Jun Huang, W. Bruce Croft

Specifically, the data selector "acts" on the source domain data to find a subset for optimization of the TL model, and the performance of the TL model can provide "rewards" in turn to update the selector.

Information Retrieval Natural Language Inference +4

Improving Multilingual Semantic Textual Similarity with Shared Sentence Encoder for Low-resource Languages

no code implementations20 Oct 2018 Xin Tang, Shanbo Cheng, Loc Do, Zhiyu Min, Feng Ji, Heng Yu, Ji Zhang, Haiqin Chen

Our approach is extended from a basic monolingual STS framework to a shared multilingual encoder pretrained with translation task to incorporate rich-resource language data.

Machine Translation Semantic Similarity +2

A Deep Relevance Model for Zero-Shot Document Filtering

1 code implementation ACL 2018 Chenliang Li, Wei Zhou, Feng Ji, Yu Duan, Haiqing Chen

In the era of big data, focused analysis for diverse topics with a short response time becomes an urgent demand.

Sentiment Analysis Text Classification +1

Memory-augmented Dialogue Management for Task-oriented Dialogue Systems

no code implementations1 May 2018 Zheng Zhang, Minlie Huang, Zhongzhou Zhao, Feng Ji, Haiqing Chen, Xiaoyan Zhu

Dialogue management (DM) decides the next action of a dialogue system according to the current dialogue state, and thus plays a central role in task-oriented dialogue systems.

Dialogue Management Task-Oriented Dialogue Systems

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