• Publications
  • Influence
Relation Classification via Convolutional Deep Neural Network
TLDR
In this paper, we exploit a convolutional deep neural network (DNN) to extract lexical and sentence level features for relation classification. Expand
  • 1,035
  • 182
  • PDF
Recurrent Convolutional Neural Networks for Text Classification
TLDR
We introduce a recurrent convolutional neural network for text classification without human-designed features. Expand
  • 1,211
  • 117
  • PDF
How to Generate a Good Word Embedding
TLDR
The authors analyze three critical components in training word embeddings: model, corpus, and training parameters. Expand
  • 220
  • 7
  • PDF
Ontology Matching with Word Embeddings
TLDR
We introduce word embeddings to the field of ontology matching. Expand
  • 22
  • 7
  • PDF
Topic-sensitive probabilistic model for expert finding in question answer communities
TLDR
We propose a topic-sensitive probabilistic model to find experts in CQA by taking into account both the link structure and the topical similarity among users. Expand
  • 77
  • 6
  • PDF
Mining Opinion Words and Opinion Targets in a Two-Stage Framework
TLDR
This paper proposes a novel two-stage method for mining opinion words and opinion targets. Expand
  • 64
  • 2
  • PDF
Hybrid Recommendation Models for Binary User Preference Prediction Problem
TLDR
This paper presents detailed information of our solutions to the task 2 of KDD Cup 2011. Expand
  • 35
  • 2
  • PDF
Walk and learn: a two-stage approach for opinion words and opinion targets co-extraction
TLDR
This paper proposes a novel two-stage method for opinion words and opinion targets co-extraction. Expand
  • 10
  • 1
  • PDF
Product Feature Mining: Semantic Clues versus Syntactic Constituents
TLDR
This paper proposes a novel product feature mining method which leverages lexical and contextual semantic clues to extract product features from online reviews. Expand
  • 14
  • PDF
Word and Document Embeddings based on Neural Network Approaches
  • Siwei Lai
  • Computer Science
  • ArXiv
  • 18 November 2016
TLDR
We make comprehensive comparisons among existing word embeddings and document representation models. Expand
  • 5
  • PDF