F
Feng Ji
Researcher at Alibaba Group
Publications - 48
Citations - 553
Feng Ji is an academic researcher from Alibaba Group. The author has contributed to research in topics: Question answering & Computer science. The author has an hindex of 10, co-authored 48 publications receiving 317 citations. Previous affiliations of Feng Ji include Fudan University & Zhejiang University.
Papers
More filters
Proceedings ArticleDOI
Simple and Effective Text Matching with Richer Alignment Features.
TL;DR: This article proposed to keep three key features available for inter-sequence alignment: original point-wise features, previous aligned features, and contextual features while simplifying all the remaining components, which is sufficient to build a fast and well-performed text matching model.
Posted Content
Simple and Effective Text Matching with Richer Alignment Features
TL;DR: A fast and strong neural approach for general purpose text matching applications and proposes to keep three key features available for inter-sequence alignment: original point-wise features, previous aligned features, and contextual features while simplifying all the remaining components.
Proceedings ArticleDOI
Review-Driven Answer Generation for Product-Related Questions in E-Commerce
TL;DR: A novel review-driven framework for answer generation for product-related questions in E-commerce, named RAGE, developed on the basis of the multi-layer convolutional architecture to facilitate speed-up of answer generation with the parallel computation.
Proceedings ArticleDOI
Learning to Selectively Transfer: Reinforced Transfer Learning for Deep Text Matching
TL;DR: A novel reinforced data selector based on the actor-critic framework is built and integrated to a DNN based transfer learning model, resulting in a Reinforced Transfer Learning (RTL) method that can significantly improve the performance of the TL model.
Journal ArticleDOI
Memory-Augmented Dialogue Management for Task-Oriented Dialogue Systems
TL;DR: Zhang et al. as mentioned in this paper proposed a memory-augmented dialogue management model that employs a memory controller and two additional memory structures (i.e., a slot-value memory and an external memory).