371 citations · 3.9k across the 110 of their papers we have counts for
12 papers · 2 filters
Distilling Knowledge Learned in BERT for Text Generation
Yen-Chun Chen, Zhe Gan, Yu Cheng +2
Large-scale pre-trained language model such as BERT has achieved great success in language understanding tasks. However, it remains an open question how to utilize BERT for languag…
Hierarchical Graph Network for Multi-hop Question Answering
Yuwei Fang, Siqi Sun, Zhe Gan +3
In this paper, we present Hierarchical Graph Network (HGN) for multi-hop question answering. To aggregate clues from scattered texts across multiple paragraphs, a hierarchical grap…
Discourse-Aware Neural Extractive Text Summarization
Jiacheng Xu, Zhe Gan, Yu Cheng +1
Recently BERT has been adopted for document encoding in state-of-the-art text summarization models. However, sentence-based extractive models often result in redundant or uninforma…
TIGEr: Text-to-Image Grounding for Image Caption Evaluation
Ming Jiang, Qiuyuan Huang, Lei Zhang +5
This paper presents a new metric called TIGEr for the automatic evaluation of image captioning systems. Popular metrics, such as BLEU and CIDEr, are based solely on text matching b…
FreeLB: Enhanced Adversarial Training for Natural Language Understanding
Chen Zhu, Yu Cheng, Zhe Gan +3
Adversarial training, which minimizes the maximal risk for label-preserving input perturbations, has proved to be effective for improving the generalization of language models. In…
What Makes A Good Story? Designing Composite Rewards for Visual Storytelling
Junjie Hu, Yu Cheng, Zhe Gan +3
Previous storytelling approaches mostly focused on optimizing traditional metrics such as BLEU, ROUGE and CIDEr. In this paper, we re-examine this problem from a different angle, b…
Domain Adaptive Text Style Transfer
Dianqi Li, Yizhe Zhang, Zhe Gan +4
Text style transfer without parallel data has achieved some practical success. However, in the scenario where less data is available, these methods may yield poor performance. In t…
Patient Knowledge Distillation for BERT Model Compression
Siqi Sun, Yu Cheng, Zhe Gan +1
Pre-trained language models such as BERT have proven to be highly effective for natural language processing (NLP) tasks. However, the high demand for computing resources in trainin…
Adversarial Domain Adaptation for Machine Reading Comprehension
Huazheng Wang, Zhe Gan, Xiaodong Liu +3
In this paper, we focus on unsupervised domain adaptation for Machine Reading Comprehension (MRC), where the source domain has a large amount of labeled data, while only unlabeled…
Tactical Rewind: Self-Correction via Backtracking in Vision-and-Language Navigation
Liyiming Ke, Xiujun Li, Yonatan Bisk +6
We present the Frontier Aware Search with backTracking (FAST) Navigator, a general framework for action decoding, that achieves state-of-the-art results on the Room-to-Room (R2R) V…
Topic-Guided Variational Autoencoders for Text Generation
Wenlin Wang, Zhe Gan, Hongteng Xu +5
We propose a topic-guided variational autoencoder (TGVAE) model for text generation. Distinct from existing variational autoencoder (VAE) based approaches, which assume a simple Ga…
Improving Sequence-to-Sequence Learning via Optimal Transport
Liqun Chen, Yizhe Zhang, Ruiyi Zhang +7
Sequence-to-sequence models are commonly trained via maximum likelihood estimation (MLE). However, standard MLE training considers a word-level objective, predicting the next word…