Using Syntactic Dependency as Local Context to Resolve Word Sense Ambiguity

Using Syntactic Dependency as Local Context to Resolve Word Sense Ambiguity
复制标题

DOI:
10.3115/976909.979626
复制
发表时间:
1997-07
期刊:
--
影响因子:
--
通讯作者:
Dekang Lin
Dekang Lin
中科院分区:
其他
文献类型:
--
作者:
Dekang Lin

文献摘要

被引文献

相似文献

大多数以前的基于语料库的算法消除歧义的一个词的分类训练从以前的使用相同的词。必须针对不同的单词训练单独的分类器。我们提出了一个算法,使用相同的知识源来消除歧义不同的话。该算法不需要一个有意义标记的语料库,并利用了这样一个事实,即两个不同的词很可能有相似的含义,如果它们出现在相同的本地上下文。
Most previous corpus-based algorithms disambiguate a word with a classifier trained from previous usages of the same word. Separate classifiers have to be trained for different words. We present an algorithm that uses the same knowledge sources to disambiguate different words. The algorithm does not require a sense-tagged corpus and exploits the fact that two different words are likely to have similar meanings if they occur in identical local contexts.