3 papers
cs.LG2018
Dynamic Self-Attention : Computing Attention over Words Dynamically for Sentence Embedding
Deunsol Yoon, Dongbok Lee, SangKeun Lee
In this paper, we propose Dynamic Self-Attention (DSA), a new self-attention mechanism for sentence embedding. We design DSA by modifying dynamic routing in capsule network (Sabour…
cs.IR2018
Utilizing Probase in Open Directory Project-based Text Classification
So-Young Jun, Dinara Aliyeva, Ji-Min Lee +1
Open Directory Project (ODP) has been successfully utilized in text classification due to its representation ability of various categories. However, ODP includes a limited number o…
cs.CL2018
Incorporating Word Embeddings into Open Directory Project based Large-scale Classification
Kang-Min Kim, Aliyeva Dinara, Byung-Ju Choi +1
Recently, implicit representation models, such as embedding or deep learning, have been successfully adopted to text classification task due to their outstanding performance. Howev…