| 基于PLSA模型的文本分割 |
| |
| 引用本文： | 石晶,戴国忠.基于PLSA模型的文本分割[J].计算机研究与发展,2007,44(2):242-248. |
| |
| 作者姓名： | 石晶 戴国忠 |
| |
| 作者单位： | 中国科学院软件研究所人机交互技术与智能信息处理实验室,北京,100080 |
| |
| 基金项目： | 国家自然科学基金
,
国家重点基础研究发展计划(973计划)
,
中国科学院软件研究所创新工程重大项目 |
| |
| 摘 要： | 文本分割在信息提取、文摘自动生成、语言建模、首语消解等诸多领域都有极为重要的应用 .基于PLSA模型的文本分割试图使隐藏于片段内的不同主题与文本表面的词、句对建立联系 .实验以汉语的整句作为基本块,尝试了多种相似性度量手段及边界估计策略,同时考虑相邻句重复的未登录词对相似值的影响,其最佳结果表明,片段边界的识别错误率为6.06%,远远低于其他同类算法 .
|
| 关 键 词： | 文本分割 概率潜在语义分析 相似性度量 边界识别 PLSA 模型 文本分割 Model Based Segmentation 算法 错误率 识别 段边界 结果 最佳 影响 相似值 未登录词 策略 边界估计 手段 相似性度量 基本块 |
| 修稿时间： | 11 30 2005 12:00AM |
Text Segmentation Based on PLSA Model |
| |
| Shi Jing,Dai Guozhong.Text Segmentation Based on PLSA Model[J].Journal of Computer Research and Development,2007,44(2):242-248. |
| |
| Authors: | Shi Jing Dai Guozhong |
| |
| Affiliation: | Computer-Human Interaction and Intelligent Information Processing Laboratory, Institute of Software, Chinese Academy of Sciences, Beljing 100080 |
| |
| Abstract: | Text segmentation is very important for many fields including information retrieval, summarization, language modeling, anaphora resolution and so on. Text segmentation based on PLSA associates different latent topics with observable pairs of word and sentence. In the experiments, Chinese whole sentences are taken as elementary blocks. Variety of similarity metrics and several approaches to discovering boundaries are tried. The influences of repetition of unknown words in adjacent sentences on similarity values are considered. The best results show the error rate is 6.06%, which is far lower than that of other algorithms of text segmentation. |
| |
| Keywords: | text segmentation probabilistic latent semantic analysis (PLSA) similarity metric boundary discovering |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
