典型文献
Lexicon-Augmented Cross-Domain Chinese Word Segmentation with Graph Convolutional Network
文献摘要：
Existing neural approaches have achieved significant progress for Chinese word segmentation(CWS).The performances of these methods tend to drop dramatically in the cross-domain scenarios due to the data distribution mismatch across domains and the out of vocabulary words problem.To address these two issues,proposes a lexicon-augmented graph convolutional net-work for cross-domain CWS.The novel model can cap-ture the information of word boundaries from all candid-ate words and utilize domain lexicons to alleviate the dis-tribution gap across domains.Experimental results on the cross-domain CWS datasets(SIGHAN-2010 and TCM)show that the proposed method successfully models in-formation of domain lexicons for neural CWS approaches and helps to achieve competitive performance for cross-domain CWS.The two problems of cross-domain CWS can be effectively solved through various interactions between characters and candidate words based on graphs.Further,experiments on the CWS benchmarks(Bakeoff-2005)also demonstrate the robustness and efficiency of the proposed method.
文献关键词：
中图分类号：
作者姓名：
YU Hao;HUANG Kaiyu;WANG Yu;HUANG Degen
作者机构：
School of Computer Science and Technology,Dalian University of Technology,Dalian 116024,China;School of Foreign Languages,Dalian University of Technology,Dalian 116024,China
文献出处：
引用格式：
[1]YU Hao;HUANG Kaiyu;WANG Yu;HUANG Degen-.Lexicon-Augmented Cross-Domain Chinese Word Segmentation with Graph Convolutional Network)[J].电子学报（英文）,2022(05):949-957
A类：
candid,lexicons,SIGHAN,Bakeoff
B类：
Lexicon,Augmented,Cross,Domain,Chinese,Word,Segmentation,Graph,Convolutional,Network,Existing,neural,approaches,have,achieved,significant,progress,segmentation,CWS,performances,these,methods,tend,drop,dramatically,scenarios,due,distribution,mismatch,across,domains,out,vocabulary,words,To,address,issues,proposes,augmented,convolutional,net,novel,cap,ture,information,boundaries,from,utilize,alleviate,gap,Experimental,results,datasets,TCM,show,that,proposed,successfully,models,helps,competitive,problems,effectively,solved,through,various,interactions,between,characters,candidate,graphs,Further,experiments,benchmarks,also,demonstrate,robustness,efficiency
AB值：
0.508494
相似文献
机标中图分类号，由域田数据科技根据网络公开资料自动分析生成，仅供学习研究参考。
