Q
Qi Zhang
Researcher at Fudan University
Publications - 194
Citations - 4566
Qi Zhang is an academic researcher from Fudan University. The author has contributed to research in topics: Computer science & Sentiment analysis. The author has an hindex of 29, co-authored 180 publications receiving 3205 citations. Previous affiliations of Qi Zhang include Massachusetts Institute of Technology & Bosch.
Papers
More filters
Proceedings ArticleDOI
Phrase Dependency Parsing for Opinion Mining
TL;DR: A novel approach for mining opinions from product reviews is presented, where it converts opinion mining task to identify product features, expressions of opinions and relations between them by taking advantage of the observation that a lot of product features are phrases.
PatentDOI
Natural language processing of disfluent sentences
Fuliang Weng,Qi Zhang +1 more
TL;DR: In this paper, an advanced model that includes new processes is provided for use as a component of an effective disfluency identifier, which tags edited words in transcribed speech, and combines a speech recognition unit in combination with a part-of-speech tagger, a disfluence identifier, and a parser.
Proceedings ArticleDOI
Keyphrase Extraction Using Deep Recurrent Neural Networks on Twitter
TL;DR: A novel deep recurrent neural network model is proposed to combine keywords and context information to perform keyphrases from tweets and the experimental results showed that the proposed method performs significantly better than previous methods.
Proceedings Article
Hashtag recommendation using attention-based convolutional neural network
Yuyun Gong,Qi Zhang +1 more
TL;DR: CNNs are adopted to perform the hashtag recommendation problem for microblogs and a novel architecture with an attention mechanism is proposed to incorporate the trigger words whose effectiveness have been experimentally evaluated in several previous works.
Proceedings Article
Adaptive Co-attention Network for Named Entity Recognition in Tweets
TL;DR: A bi-directional long short term memory network with conditional random fields and an adaptive co-attention network is extended to achieve named entity recognition for tweets to make full use of textual and visual information.