2020/06/14 by Duc-Vu Nguyen, Nguyen, Duc-Vu, Dang Van Thin +5
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Handwritten Text Recognition Techniques #Natural Language Processing Techniques #Speech Recognition and Synthesis
paper · pdf · doi:10.48550/arxiv.2006.07804
openalex publication_date 2020/06/14 · openalex created_date 2022/07/26 · openalex updated_date 2026/07/28
In this paper, we approach Vietnamese word segmentation as a binary\nclassification by using the Support Vector Machine classifier. We inherit\nfeatures from prior works such as n-gram of syllables, n-gram of syllable\ntypes, and checking conjunction of adjacent syllables in the dictionary. We\npropose two novel ways to feature extraction, one to reduce the overlap\nambiguity and the other to increase the ability to predict unknown words\ncontaining suffixes. Different from UETsegmenter and RDRsegmenter, two\nstate-of-the-art Vietnamese word segmentation methods, we do not employ the\nlongest matching algorithm as an initial processing step or any post-processing\ntechnique. According to experimental results on benchmark Vietnamese datasets,\nour proposed method obtained a better F1-score than the prior state-of-the-art\nmethods UETsegmenter, and RDRsegmenter.\n