• Publications
  • Influence
Relation Classification via Convolutional Deep Neural Network
TLDR
This paper exploits a convolutional deep neural network (DNN) to extract lexical and sentence level features from the output of pre-existing natural language processing systems and significantly outperforms the state-of-the-art methods.
Recurrent Convolutional Neural Networks for Text Classification
TLDR
A recurrent convolutional neural network is introduced for text classification without human-designed features to capture contextual information as far as possible when learning word representations, which may introduce considerably less noise compared to traditional window-based neural networks.
Topic-sensitive probabilistic model for expert finding in question answer communities
TLDR
This study proposes a topic-sensitive probabilistic model, which is an extension of PageRank algorithm to find experts in CQA, which significantly outperforms the traditional link analysis techniques and achieves the state-of-the-art performance for expert finding in C QA.
How to Generate a Good Word Embedding
TLDR
The authors analyze three critical components in training word embeddings: model, corpus, and training parameters, and evaluate each word embedding in three ways: analyzing its semantic properties, using it as a feature for supervised tasks, and using it to initialize neural networks.
Ontology Matching with Word Embeddings
TLDR
The experimental results show that in element-level matching, word embeddings could achieve better performance than previous methods.
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, which naturally incorporates syntactic patterns in a Sentiment Graph to extract opinion word/target candidates and adopts a self-learning strategy to refine the results.
Hybrid Recommendation Models for Binary User Preference Prediction Problem
TLDR
The task 2 is called binary user preference prediction problem in the paper because it aims at separating tracks rated highly by specific users from tracks not rated by them, and the solutions of this task can be easily applied to binary user behavior data.
Walk and learn: a two-stage approach for opinion words and opinion targets co-extraction
TLDR
A novel two-stage method for opinion words and opinion targets co-extraction using a Sentiment Graph Walking algorithm, which naturally incorporates syntactic patterns in a graph to extract opinion word/target candidates.
Product Feature Mining: Semantic Clues versus Syntactic Constituents
TLDR
Experimental results show that the semantics-based method significantly outperforms conventional syntaxbased approaches, which not only mines product features more accurately, but also extracts more infrequent product features.
Click-Through Prediction for Sponsored Search Advertising with Hybrid Models
TLDR
A rank-based ensemble method is proposed which greatly improves the results of the model and the final submission is based on BPR, SVM and MLE.
...
...