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