activity
20182020
most citedA Dual Reinforcement Learning Framework for Unsupervised Text Style Transfer

41 citations · 60 across the 5 of their papers we have counts for

collaborators
Showing cs.CLShow all

11 papers · 1 filter

cs.CL202014 cited

CAPT: Contrastive Pre-Training for Learning Denoised Sequence Representations

Fuli Luo, Pengcheng Yang, Shicheng Li +2

Pre-trained self-supervised models such as BERT have achieved striking success in learning sequence representations, especially for natural language processing. These models typica…

cs.CL20202 cited

Inductively Representing Out-of-Knowledge-Graph Entities by Optimal Estimation Under Translational Assumptions

Damai Dai, Hua Zheng, Fuli Luo +3

Conventional Knowledge Graph Completion (KGC) assumes that all test entities appear during training. However, in real-world scenarios, Knowledge Graphs (KG) evolve fast with out-of…

cs.CL20191 cited

Visual Agreement Regularized Training for Multi-Modal Machine Translation

Pengcheng Yang, Boxing Chen, Pei Zhang +1

Multi-modal machine translation aims at translating the source sentence into a different language in the presence of the paired image. Previous work suggests that additional visual…

cs.CL20192 cited

Pun-GAN: Generative Adversarial Network for Pun Generation

Fuli Luo, Shunyao Li, Pengcheng Yang +4

In this paper, we focus on the task of generating a pun sentence given a pair of word senses. A major challenge for pun generation is the lack of large-scale pun corpus to guide th…

cs.CL2019

Key Fact as Pivot: A Two-Stage Model for Low Resource Table-to-Text Generation

Shuming Ma, Pengcheng Yang, Tianyu Liu +3

Table-to-text generation aims to translate the structured data into the unstructured text. Most existing methods adopt the encoder-decoder framework to learn the transformation, wh…

cs.CL201941 cited

A Dual Reinforcement Learning Framework for Unsupervised Text Style Transfer

Fuli Luo, Peng Li, Jie Zhou +4

Unsupervised text style transfer aims to transfer the underlying style of text but keep its main content unchanged without parallel data. Most existing methods typically follow two…