activity
20172019
most citedLinearFold: linear-time approximate RNA folding by 5'-to-3' dynamic programming and beam search

255 citations · 262 across the 4 of their papers we have counts for

collaborators

5 papers

q-bio.BM2019255 cited

LinearFold: linear-time approximate RNA folding by 5'-to-3' dynamic programming and beam search

Liang Huang, He Zhang, Dezhong Deng +4

Motivation: Predicting the secondary structure of an RNA sequence is useful in many applications. Existing algorithms (based on dynamic programming) suffer from a major limitation:…

cs.CL2018

When to Finish? Optimal Beam Search for Neural Text Generation (modulo beam size)

Liang Huang, Kai Zhao, Mingbo Ma

In neural text generation such as neural machine translation, summarization, and image captioning, beam search is widely used to improve the output text quality. However, in the ne…

cs.CL20171 cited

OSU Multimodal Machine Translation System Report

Mingbo Ma, Dapeng Li, Kai Zhao +1

This paper describes Oregon State University's submissions to the shared WMT'17 task "multimodal translation task I". In this task, all the sentence pairs are image captions in dif…

cs.CL20175 cited

Jointly Trained Sequential Labeling and Classification by Sparse Attention Neural Networks

Mingbo Ma, Kai Zhao, Liang Huang +2

Sentence-level classification and sequential labeling are two fundamental tasks in language understanding. While these two tasks are usually modeled separately, in reality, they ar…

cs.CL20171 cited

Joint Syntacto-Discourse Parsing and the Syntacto-Discourse Treebank

Kai Zhao, Liang Huang

Discourse parsing has long been treated as a stand-alone problem independent from constituency or dependency parsing. Most attempts at this problem are pipelined rather than end-to…