J
Jipeng Qiang
Researcher at Yangzhou University
Publications - 75
Citations - 778
Jipeng Qiang is an academic researcher from Yangzhou University. The author has contributed to research in topics: Computer science & Sentence. The author has an hindex of 10, co-authored 58 publications receiving 395 citations. Previous affiliations of Jipeng Qiang include University of Massachusetts Boston & Hefei University of Technology.
Papers
More filters
Journal ArticleDOI
Short Text Topic Modeling Techniques, Applications, and Performance: A Survey
TL;DR: This survey conducts a comprehensive review of various short text topic modeling techniques proposed in the literature, and presents three categories of methods based on Dirichlet multinomial mixture, global word co-occurrences, and self-aggregation, with example of representative approaches in each category and analysis of their performance on various tasks.
Book ChapterDOI
Topic Modeling over Short Texts by Incorporating Word Embeddings
TL;DR: This paper proposed Embedding-based Topic Model (ETM) to learn latent topics from short texts by aggregating short texts into long pseudo-texts and using a Markov Random Field regularized model that gives correlated words a better chance to be put into the same topic.
Proceedings Article
Text simplification using Neural Machine Translation
TL;DR: Original English and simplified English as two languages are regarded, and a NMT model–Recurrent Neural Network (RNN) encoder-decoder on TS is applied to make the neural network to learn text simplification rules by itself.
Journal ArticleDOI
Multi-document summarization using closed patterns
TL;DR: A pattern-based model for generic multi-document summarization is presented, which exploits closed patterns to extract the most salient sentences from a document collection and reduce redundancy in the summary.
Posted Content
Lexical Simplification with Pretrained Encoders
TL;DR: Experimental results show that this approach obtains obvious improvement compared with these baselines leveraging linguistic databases and parallel corpus, outperforming the state-of-the-art by more than 12 Accuracy points on three well-known benchmarks.