463 citations · 5.1k across the 190 of their papers we have counts for
7 papers · 2 filters
Syntax-Infused Transformer and BERT models for Machine Translation and Natural Language Understanding
Dhanasekar Sundararaman, Vivek Subramanian, Guoyin Wang +4
Attention-based models have shown significant improvement over traditional algorithms in several NLP tasks. The Transformer, for instance, is an illustrative example that generates…
Ouroboros: On Accelerating Training of Transformer-Based Language Models
Qian Yang, Zhouyuan Huo, Wenlin Wang +2
Language models are essential for natural language processing (NLP) tasks, such as machine translation and text summarization. Remarkable performance has been demonstrated recently…
Learning Compressed Sentence Representations for On-Device Text Processing
Dinghan Shen, Pengyu Cheng, Dhanasekar Sundararaman +5
Vector representations of sentences, trained on massive text corpora, are widely used as generic sentence embeddings across a variety of NLP problems. The learned representations a…
Improving Textual Network Embedding with Global Attention via Optimal Transport
Liqun Chen, Guoyin Wang, Chenyang Tao +6
Constituting highly informative network embeddings is an important tool for network analysis. It encodes network topology, along with other useful side information, into low-dimens…
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…
Towards Generating Long and Coherent Text with Multi-Level Latent Variable Models
Dinghan Shen, Asli Celikyilmaz, Yizhe Zhang +4
Variational autoencoders (VAEs) have received much attention recently as an end-to-end architecture for text generation with latent variables. In this paper, we investigate several…
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…