127 citations · 498 across the 73 of their papers we have counts for
7 papers · 2 filters
Effective Representation for Easy-First Dependency Parsing
Zuchao Li, Jiaxun Cai, Hai Zhao
Easy-first parsing relies on subtree re-ranking to build the complete parse tree. Whereas the intermediate state of parsing processing is represented by various subtrees, whose int…
Fast Neural Chinese Word Segmentation for Long Sentences
Sufeng Duan, Jiangtong Li, Hai Zhao
Rapidly developed neural models have achieved competitive performance in Chinese word segmentation (CWS) as their traditional counterparts. However, most of methods encounter the c…
Attentive Semantic Role Labeling with Boundary Indicator
Zhuosheng Zhang, Shexia He, Zuchao Li +1
The goal of semantic role labeling (SRL) is to discover the predicate-argument structure of a sentence, which plays a critical role in deep processing of natural language. This pap…
Explicit Contextual Semantics for Text Comprehension
Zhuosheng Zhang, Yuwei Wu, Zuchao Li +1
Who did what to whom is a major focus in natural language understanding, which is right the aim of semantic role labeling (SRL) task. Despite of sharing a lot of processing charact…
Effective Character-augmented Word Embedding for Machine Reading Comprehension
Zhuosheng Zhang, Yafang Huang, Pengfei Zhu +1
Machine reading comprehension is a task to model relationship between passage and query. In terms of deep learning framework, most of state-of-the-art models simply concatenate wor…
Finding Better Subword Segmentation for Neural Machine Translation
Yingting Wu, Hai Zhao
For different language pairs, word-level neural machine translation (NMT) models with a fixed-size vocabulary suffer from the same problem of representing out-of-vocabulary (OOV) w…
SJTU-NLP at SemEval-2018 Task 9: Neural Hypernym Discovery with Term Embeddings
Zhuosheng Zhang, Jiangtong Li, Hai Zhao +1
This paper describes a hypernym discovery system for our participation in the SemEval-2018 Task 9, which aims to discover the best (set of) candidate hypernyms for input concepts o…