Transition-Based Neural Word Segmentation Using Word-Level Features

Abstract


 
 
 Character-based and word-based methods are two different solutions for Chinese word segmentation, the former exploiting sequence labeling models over characters and the latter using word-level features. Neural models have been exploited for character-based Chinese word segmentation, giving high accuracies by making use of external character embeddings, yet requiring less feature engineering. In this paper, we study a neural model for word-based Chinese word segmentation, by replacing the manually-designed discrete features with neural features in a transition-based word segmentation framework. Experimental results demonstrate that word features lead to comparable performance to the best systems in the literature, and a further combination of discrete and neural features obtains top accuracies on several benchmarks.
 
 

End-to-end Semantic Role Labeling with Neural Transition-based Model

“…Alternatively, the transition-based framework offers another solution for end-to-end modeling, which is totally orthogonal to the graph-based models. Transition-based models have been widely exploited for end-to-end sequence labeling (Zhang and Clark 2010;Lyu, Zhang, and Ji 2016;Zhang, Zhang, and Fu 2018), structural parsing (Zhou et al 2015;Dyer et al 2015;Yuan, Jiang, and Tu 2019) and relation extraction (Wang et al 2018;, which are closely related to SRL. These models can also achieve very competitive performances for a range of tasks, and meanwhile maintain high efficiencies with linear-time decoding complexity.…”

End-to-end Semantic Role Labeling with Neural Transition-based Model

“…Alternatively, the transition-based framework offers another solution for end-to-end modeling, which is totally orthogonal to the graph-based models. Transition-based models have been widely exploited for end-to-end sequence labeling (Zhang and Clark 2010;Lyu, Zhang, and Ji 2016;Zhang, Zhang, and Fu 2018), structural parsing (Zhou et al 2015;Dyer et al 2015;Yuan, Jiang, and Tu 2019) and relation extraction (Wang et al 2018;, which are closely related to SRL. These models can also achieve very competitive performances for a range of tasks, and meanwhile maintain high efficiencies with linear-time decoding complexity.…”