什么是用于词性标注的优秀Java库？ [英] What is a good Java library for Parts-Of-Speech tagging?
问题描述
我正在寻找Java中的一个好的开源 POS Tagger 。这是我到目前为止所提出的。
I'm looking for a good open source POS Tagger in Java. Here's what I have come up with so far.
- LingPipe
- Stanford
- LBJ
- FastTag
有人有任何建议吗？
推荐答案
你在找吗？标记特定域中的POS？大多数通用标记符都是通过新闻专线文本进行培训的。通常，当您在特定域（例如生物医学文本）中使用它们时，它们表现不佳。还有其他专门为这些领域培训过的标记，例如 dTagger （java）for biomedical text。
Are you looking to tag POS in a specific domain? Most of the general purpose taggers are trained on newswire text. Typically they don't perform well when you are using them in specific domains (such and biomedical text). There are other taggers specifically trained for such domains such as dTagger (java) for biomedical text.
对于newswire文本，Adwait Ratnaparkhi的 MXPOST 非常好，是我推荐的。
For newswire text, Adwait Ratnaparkhi's MXPOST is very good and is the one I would recommend.
其他Java实现包括：
Other Java implementations include:
- MontyLingua
- Berkeley Parser （不是真正的POS标记器，但所有完整的解析器通常都包含POS标记器.Google用于 Java语法分析器，你会发现很多。）
- QTag
- LBJ
- MontyLingua
- Berkeley Parser (Not really a POS tagger but all full blown parsers will typically include POS taggers. Google for Java syntactic parsers and you will find many.)
- QTag
- LBJ
OpenNLP 和 Lingpipe 已发布通过其他海报也相当不错。
OpenNLP and Lingpipe as posted by the other posters are also pretty decent.
有关POS标签最新技术的信息可以找到这里。如您所见， LTAG-Spinal （另一张海报也提到）排名最佳现在，但各种标签的变化并不多。我自己没有使用过LTAG。
Info on the state-of-the-art on POS tagging can be found here. As you can see LTAG-Spinal (also mentioned by another poster) ranks best as of now, but the variation across the various taggers is not much. I have not used LTAG myself.
另请注意，POS标记的基准性能约为90％。基线意味着 - （a）用词典中最频繁的POS标签标记每个单词，（b）将每个未知单词标记为名词。
Also note that the baseline performance for POS tagging is about 90%. Baseline means - (a) tag every word by most frequent POS tag from a lexicon, and (b) tag every unknown word as a noun.
这篇关于什么是用于词性标注的优秀Java库？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！
