 |
|
|
|
 |
 |
 |
|
 |
|
 |
|
|
| 王厚峰,王波.基于句子对齐的汉语句法结构推导的计算模型.软件学报,2007,18(3):538-546 |
| 基于句子对齐的汉语句法结构推导的计算模型 |
| A Computational Model for Chinese Syntactic Structure Induction Based on Sentence Alignment |
| 投稿时间：2004-01-26 修订日期：2006-04-12 |
| DOI： |
| 中文关键词: 句子对齐 无指导学习 边界摩擦 相同优先 相异优先 汉语句法结构推导 |
| 英文关键词:sentence alignment unsupervised learning boundary friction similarity priority difference priority Chinese syntactic structure induction |
| 基金项目:Supported by the National Natural Science Foundation of China under Grant Nos.60473138,60675035(国家自然科学基金) |
|
| 摘要点击次数: 3211 |
| 全文下载次数: 2750 |
| 中文摘要: |
| 基于句子的相似性,提出了无指导的汉语句法结构推导方法.基本思想是:首先,在汉语句子库的基础上,通过句对之间的对齐,得到交替的相同片断和相异片断.然后,根据相同片断优先或相异片断优先策略,选取相应的对齐片断作为句子成分候选,并对可能因片断交叉而导致边界摩擦的候选进行歧义消解.最后,通过逐步归约句子成分,推导出汉语句法结构树.为了避免对齐过程中词的稀疏问题,还对部分具有明显规律的词事先作了归类处理.分别以词、词性以及词联合词性作为句子基本构成单元,评测了推导的句法结果.测试结果表明:对于3种构成单元,相异片断 |
| 英文摘要: |
| This paper introduces an unsupervised learning framework of Chinese syntactic structure based sentences similarity. First, all sentence pairs in the Chinese sentence corpus are aligned, and each pair is partitioned into similarity segmentations and different ones which alternately occur, Then, aligned similarity segmentations or different ones are selected as potential constituent candidates based on the strategy of similarity priority or of difference priority respectively. As the boundary friction may be introduced in the later step, its disambiguation is further carried out. Finally, by inducing sentence constituents, the syntactic structures are learned. In order to reduce word sparseness in the process, some words are replaced by classes in advance. Three forms of the sentence units, such as the sequence of words, the sequence of POS (part of speech)-tags and the sequence of words with POS-tag, are examined and the learned syntactic structures are evaluated respectively. The results show that different priority strategy achieves a better performance than the similarity one, and the Fs are above 46% for all three forms, with the best one being 49.52%, which is better than those having been reported. |
|
HTML 下载PDF全文 查看/发表评论 下载PDF阅读器 |
|
|
|
|
|
|
 |
|
|
|
|
 |
|
 |
|
 |
|
