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.
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.
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.
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.
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.
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.
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.
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.