• Publications
  • Influence
Implicit feature identification via hybrid association rule mining
TLDR
In sentiment analysis, a finer-grained opinion mining method not only focuses on the view of product itself, but also focuses on product features, which can be a component or attribute of the product. Expand
  • 54
  • 6
A hybrid term-term relations analysis approach for topic detection
TLDR
We propose a hybrid relations analysis approach to integrate semantic relations and co-occurrence relations for topic detection. Expand
  • 33
  • 2
Incorporating External Knowledge into Machine Reading for Generative Question Answering
TLDR
We propose a new neural model, Knowledge-Enriched Answer Generator (KEAG), which is able to compose a natural answer by exploiting and aggregating evidence from all four information sources available: question, passage, vocabulary and knowledge. Expand
  • 12
  • 2
  • PDF
Implicit feature identification in Chinese reviews using explicit topic mining model
TLDR
We first extend a popular topic modeling method, called Latent Dirichlet Allocation (LDA), to construct an explicit topic model in which each topic is pre-defined. Expand
  • 57
  • 1
Utilizing Generative Adversarial Networks for Recommendation based on Ratings and Reviews
TLDR
In this paper, we propose Rating and Review Generative Adversarial Networks (RRGAN), an innovative framework for recommendation, in which the generative model and discriminative model play a minimax game. Expand
  • 2
  • 1
  • PDF
WUST at the NTCIR-14 FinNum Task
This paper describes our system in the FinNum task at NTCIR-14, and the FinNum task is dedicated to identifying the category of a numeral from the financial social media data, i.e. tweet, forExpand
  • 1
  • 1
  • PDF
Improving Whole-Heart CT Image Segmentation by Attention Mechanism
TLDR
In this paper, we proposed three modified attention models, including simple negative example mining (SNEM), attention gate (AG) and U-CliqueNet (UCNet), to lead the deep learning network to focus on more salient information. Expand
  • 1
Semantic multi-grain mixture topic model for text analysis
TLDR
A new model, mgMTM (multi-grain mixture topic model) based on STG is proposed to model grain topics. Expand
  • 7
A negotiation methodology for multidisciplinary collaborative product design
TLDR
A new negotiation model is given by introducing concepts of concession, satisfaction degree and strategy power exponent. Expand
  • 10
A Multi-Step Approach Framework for Freight Forecasting of River-Sea Direct Transport without Direct Historical Data
The freight forecasting of river-sea direct transport (RSDT) is crucial for the policy making of river-sea transportation facilities and the decision-making of relevant port and shipping companies.Expand
  • 2
  • PDF