Zobrazeno 1 - 10
of 20
pro vyhledávání: '"Dinghan Shen"'
Autor:
Yuan-Fang Wang, Xin Wang, Dinghan Shen, William Yang Wang, Qiuyuan Huang, Lei Zhang, Asli Celikyilmaz, Jianfeng Gao
Publikováno v:
IEEE Transactions on Pattern Analysis and Machine Intelligence. 43:4205-4216
Vision-language navigation (VLN) is the task of navigating an embodied agent to carry out natural language instructions inside real 3D environments. In this paper, we study how to address three critical challenges for this task: the cross-modal groun
Publikováno v:
ACL/IJCNLP (1)
Fine-tuning large pre-trained models with task-specific data has achieved great success in NLP. However, it has been demonstrated that the majority of information within the self-attention networks is redundant and not utilized effectively during the
Autor:
Qian Yang, Chunyuan Li, Yizhe Zhang, Lawrence Carin, Wenlin Wang, Jianqiao Li, Liqun Chen, Yuh-Chen Lin, Hao Fu, Chenyang Tao, Guoyin Wang, Dinghan Shen, Ruiyi Zhang
Publikováno v:
EMNLP (1)
Neural language models are often trained with maximum likelihood estimation (MLE), where the next word is generated conditioned on the ground-truth word tokens. During testing, however, the model is instead conditioned on previously generated tokens,
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4cb90e0003c412a95b63c2561e0d0d31
http://arxiv.org/abs/2010.05994
http://arxiv.org/abs/2010.05994
Autor:
Wenlin Wang, Zheng Wen, Changyou Chen, Ruiyi Zhang, Zhe Gan, Dinghan Shen, Lawrence Carin, Guoyin Wang
Publikováno v:
ACL
Auto-regressive text generation models usually focus on local fluency, and may cause inconsistent semantic meaning in long text generation. Further, automatically generating words with similar semantics is challenging, and hand-crafted linguistic rul
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a20c60bf3c9e0c6983229a4f66e0673d
http://arxiv.org/abs/2005.01279
http://arxiv.org/abs/2005.01279
Publikováno v:
ACL
Generative semantic hashing is a promising technique for large-scale information retrieval thanks to its fast retrieval speed and small memory footprint. For the tractability of training, existing generative-hashing methods mostly assume a factorized
Autor:
Christopher Malon, Martin Renqiang Min, Pengyu Cheng, Yitong Li, Dinghan Shen, Yizhe Zhang, Lawrence Carin
Publikováno v:
ACL
Learning disentangled representations of natural language is essential for many NLP tasks, e.g., conditional text generation, style transfer, personalized dialogue systems, etc. Similar problems have been studied extensively for other forms of data,
Publikováno v:
EMNLP/IJCNLP (1)
Hashing is promising for large-scale information retrieval tasks thanks to the efficiency of distance evaluation between binary codes. Generative hashing is often used to generate hashing codes in an unsupervised way. However, existing generative has
Autor:
Zhe Gan, Lawrence Carin, Wenlin Wang, Ruiyi Zhang, Dinghan Shen, Hongteng Xu, Guoyin Wang, Changyou Chen
Publikováno v:
NAACL-HLT (1)
We propose a topic-guided variational auto-encoder (TGVAE) model for text generation. Distinct from existing variational auto-encoder (VAE) based approaches, which assume a simple Gaussian prior for latent code, our model specifies the prior as a Gau
Autor:
Asli Celikyilmaz, Lawrence Carin, Dhanasekar Sundararaman, Xinyuan Zhang, Qian Yang, Dinghan Shen, Meng Tang, Pengyu Cheng
Publikováno v:
Scopus-Elsevier
ACL (1)
ACL (1)
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 are generally assumed to be continuous and real-valued, giving rise to
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::25f6b14daeb1a366058b956a4754cf9d
Autor:
Liqun Chen, Dinghan Shen, Asli Celikyilmaz, Lawrence Carin, Jianfeng Gao, Yizhe Zhang, Xin Wang
Publikováno v:
Scopus-Elsevier
ACL (1)
ACL (1)
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 multi-level structures to learn a VAE model to generate long, and coh
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::dafc5fafdf210f0f5620b6af8432f4fb