P
Piji Li
Researcher at Tencent
Publications - 116
Citations - 2489
Piji Li is an academic researcher from Tencent. The author has contributed to research in topics: Computer science & Automatic summarization. The author has an hindex of 21, co-authored 91 publications receiving 1734 citations. Previous affiliations of Piji Li include The Chinese University of Hong Kong & Fudan University.
Papers
More filters
Proceedings ArticleDOI
Neural Rating Regression with Abstractive Tips Generation for Recommendation
TL;DR: A deep learning based framework named NRT is proposed which can simultaneously predict precise ratings and generate abstractive tips with good linguistic quality simulating user experience and feelings.
Proceedings ArticleDOI
Deep Recurrent Generative Decoder for Abstractive Text Summarization
TL;DR: A new framework for abstractive text summarization based on a sequence-to-sequence oriented encoder-decoder model equipped with a deep recurrent generative decoder (DRGN) achieves improvements over the state-of-the-art methods.
Proceedings ArticleDOI
Aspect Term Extraction with History Attention and Selective Transformation
TL;DR: The authors extract explicit aspect expressions from online user reviews using both opinion summary and aspect detection history, which can be used to boost aspect prediction performance and improve the aspect term extraction performance of ATE.
Proceedings ArticleDOI
Social Collaborative Viewpoint Regression with Explainable Recommendations
TL;DR: This paper proposes a latent variable model, called social collaborative viewpoint regression (sCVR), for predicting item ratings based on user opinions and social relations, and uses so-called viewpoints, represented as tuples of a concept, topic, and a sentiment label from both user reviews and trusted social relations.
Journal ArticleDOI
A Unified Model for Opinion Target Extraction and Target Sentiment Prediction
TL;DR: This paper aims to solve the complete task of target-based sentiment analysis in an end-to-end fashion, and presents a novel unified model which applies a unified tagging scheme.