Zobrazeno 1 - 10
of 11
pro vyhledávání: '"Hongzhao Huang"'
Autor:
Chunli Su, Yanzhen Tao, Xianjun Xie, Hongjie Pan, Fugui Yan, Hanbin Zeng, Shuang Gao, Hongzhao Huang
Publikováno v:
Journal of Soils and Sediments. 23:1281-1294
Publikováno v:
Journal of Physics: Conference Series. 2200:012010
The principle of Fused Deposition Modeling (FDM) is basically that the micro-nozzle moves along the part in the filling track under the computer using some low viscosity material heated to an appropriate temperature without manual intervention. Even
Publikováno v:
ICASSP
We explore two adaptation approaches of deep Transformer based neural language models (LMs) for automatic speech recognition. The first approach is a pretrain-finetune framework, where we first pretrain a Transformer LM on a large-scale text corpus f
Autor:
Hongzhao Huang, Xiaohui Zhang, Christian Fuegen, Andros Tjandra, Jay Mahadeokar, Frank Zhang, Due Le, Yongqiang Wang, Alex Xiao, Chunxi Liu, Michael L. Seltzer, Abdelrahman Mohamed, Geoffrey Zweig
Publikováno v:
ICASSP
We propose and evaluate transformer-based acoustic models (AMs) for hybrid speech recognition. Several modeling choices are discussed in this work, including various positional embedding methods and an iterated loss to enable training deep transforme
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bf1e2f16829fa1ddd1b3d84730bfffea
Autor:
Kevin Knight, Hongzhao Huang, Yizhou Sun, Jiawei Han, Chin-Yew Lin, Boliang Zhang, Sujian Li, Bulent Yener, Heng Ji, Xiaoman Pan, Zhen Wen
Publikováno v:
ACL (1)
People create morphs, a special type of fake alternative names, to achieve certain communication goals such as expressing strong sentiment or evading censors. For example, “Black Mamba”, the name for a highly venomous snake, is a morph that Kobe
Autor:
Hongzhao Huang, Larry Heck
Publikováno v:
GlobalSIP
This paper presents a novel method to learn neural knowledge graph embeddings. The embeddings are used to compute semantic relatedness in a coherence-based semantic parser. The approach learns embeddings directly from structured knowledge representat
Autor:
Haibo Li, Tongtao Zhang, Min-Hsuan Tsai, Hongzhao Huang, Thomas S. Huang, Heng Ji, Shen-Fu Tsai
Publikováno v:
VL@COLING
Publikováno v:
ACL (1)
Wikification for tweets aims to automatically identify each concept mention in a tweet and link it to a concept referent in a knowledge base (e.g., Wikipedia). Due to the shortness of a tweet, a collective inference model incorporating global evidenc
Autor:
Bülent Yener, Hongzhao Huang, Heng Ji, Boliang Zhang, Xiaoman Pan, Yizhou Sun, Jiawei Han, Kevin Knight, Zhen Wen
Publikováno v:
ACL (2)
Internet users are keen on creating different kinds of morphs to avoid censorship, express strong sentiment or humor. For example, in Chinese social media, users often use the entity morph “¹ ? b (Instant Noodles)” to refer to “h 8 · (Zhou Yo
Publikováno v:
IPSN
This demonstration illustrates an information aggregation and summarization service for social sensing applications. Social sensing, using mobile phones and other networked devices in the possession of individuals, has gained significant popularity i