most citedLattice-Based Transformer Encoder for Neural Machine Translation

9 citations · 9 across the 2 of their papers we have counts for

collaborators

8 papers

cs.CV2019

Zero-Shot Sketch-Based Image Retrieval with Structure-aware Asymmetric Disentanglement

Jiangtong Li, Zhixin Ling, Li Niu +1

The goal of Sketch-Based Image Retrieval (SBIR) is using free-hand sketches to retrieve images of the same category from a natural image gallery. However, SBIR requires all test ca…

cs.CL2019

Subword ELMo

Jiangtong Li, Hai Zhao, Zuchao Li +2

Embedding from Language Models (ELMo) has shown to be effective for improving many natural language processing (NLP) tasks, and ELMo takes character information to compose word rep…

cs.CL20199 cited

Lattice-Based Transformer Encoder for Neural Machine Translation

Fengshun Xiao, Jiangtong Li, Hai Zhao +2

Neural machine translation (NMT) takes deterministic sequences for source representations. However, either word-level or subword-level segmentations have multiple choices to split…

cs.CL2019

Judging Chemical Reaction Practicality From Positive Sample only Learning

Shu Jiang, Zhuosheng Zhang, Hai Zhao +4

Chemical reaction practicality is the core task among all symbol intelligence based chemical information processing, for example, it provides indispensable clue for further automat…

cs.CL2018

Effective Subword Segmentation for Text Comprehension

Zhuosheng Zhang, Hai Zhao, Kangwei Ling +4

Representation learning is the foundation of machine reading comprehension and inference. In state-of-the-art models, character-level representations have been broadly adopted to a…

cs.CL2018

Lingke: A Fine-grained Multi-turn Chatbot for Customer Service

Pengfei Zhu, Zhuosheng Zhang, Jiangtong Li +2

Traditional chatbots usually need a mass of human dialogue data, especially when using supervised machine learning method. Though they can easily deal with single-turn question ans…