The paper proposes a unified framework to combine the advantages of the fast one-at-a-time approach and the high-performance all-at-once approach to perform Chinese Word Segmentation(CWS) and Part-of-Speech(PoS) taggi...The paper proposes a unified framework to combine the advantages of the fast one-at-a-time approach and the high-performance all-at-once approach to perform Chinese Word Segmentation(CWS) and Part-of-Speech(PoS) tagging.In this framework,the input of the PoS tagger is a candidate set of several CWS results provided by the CWS model.The widely used one-at-a-time approach and all-at-once approach are two extreme cases of the proposed candidate-based approaches.Experiments on Penn Chinese Treebank 5 and Tsinghua Chinese Treebank show that the generalized candidate-based approach outperforms one-at-a-time approach and even the all-at-once approach.The candidate-based approach is also faster than the time-consuming all-at-once approach.The authors compare three different methods based on sentence,words and character-intervals to generate the candidate set.It turns out that the word-based method has the best performance.展开更多
基金supported by the National Natural Science Foundation of China under GrantNo.60873174
文摘The paper proposes a unified framework to combine the advantages of the fast one-at-a-time approach and the high-performance all-at-once approach to perform Chinese Word Segmentation(CWS) and Part-of-Speech(PoS) tagging.In this framework,the input of the PoS tagger is a candidate set of several CWS results provided by the CWS model.The widely used one-at-a-time approach and all-at-once approach are two extreme cases of the proposed candidate-based approaches.Experiments on Penn Chinese Treebank 5 and Tsinghua Chinese Treebank show that the generalized candidate-based approach outperforms one-at-a-time approach and even the all-at-once approach.The candidate-based approach is also faster than the time-consuming all-at-once approach.The authors compare three different methods based on sentence,words and character-intervals to generate the candidate set.It turns out that the word-based method has the best performance.
