有没有办法使用OpenNLP获得句子的主题？ [英] Is there a way to get the subject of a sentence using OpenNLP?
问题描述
有没有办法使用OpenNLP获得句子的主题？
我正在尝试识别用户句子中最重要的部分。一般来说，用户会向我们的引擎提交句子，我们想知道该句话的核心主题是什么。
Is there a way to get the subject of a sentence using OpenNLP? I'm trying to identify the most important part of a users sentence. Generally, users will be submitting sentences to our "engine" and we want to know exactly what the core topic is of that sentence.
目前我们正在使用openNlp：
Currently we are using openNlp to:
- 判断句子
- 识别句子的名词短语，动词等
- 识别句子的所有主题
- （未完成！）确定句子的核心主题
- Chunk the sentence
- Identify the noun-phrase, verbs, etc of the sentence
- Identify all "topics" of the sentence
- (NOT YET DONE!) Identify the "core topic" of the sentence
如果您有任何好主意，请告诉我。
Please let me know if you have any bright ideas..
推荐答案
依赖性解析器
如果您有兴趣提取语法关系，例如单词或短语是句子的主语，您应该真的使用依赖解析器。虽然OpenNLP确实支持短语结构解析，但我认为它还没有进行依赖解析。
If you're interested in extracting grammatical relations such as what word or phrase is the subject of a sentence, you should really use a dependency parser. While OpenNLP does support phrase structure parsing, I don't think it does dependency parsing yet.
开源软件
用Java编写的支持依赖性解析的软件包包括：
Packages written in Java that support dependency parsing include:
- MaltParser
- MSTParser
- Stanford Parser （演示，请参阅类型依赖项部分）
- RelEx
- MaltParser
- MSTParser
- Stanford Parser (demo, see typed dependencies section)
- RelEx
其中，斯坦福分析师是最准确的。但是，MaltParser的某些配置可能非常快（ Cer et al.2010 ）。
Of these, the Stanford Parser is the most accurate. However, some configurations of the MaltParser can be insanely fast (Cer et al. 2010).
这篇关于有没有办法使用OpenNLP获得句子的主题？的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！
