词性赋码语料库的检索与正则表达式的编写 POS tagged corpus search + regex
- 主题发起人 xujiajin
- 时间
xusun575
高级会员
回覆: 词性赋码语料库的检索与正则表达式的编写 POS tagged corpus search + regex
PatterrnBuilder下载后打不开 能否麻烦哪位老师能发我邮箱：mccharlie@163.com
PatterrnBuilder下载后打不开 能否麻烦哪位老师能发我邮箱：mccharlie@163.com
回覆: 词性赋码语料库的检索与正则表达式的编写 POS tagged corpus search + regex
i'm just a beginner and i'm rather concerned about what kind of automatic pos tagging tools can be used before we use the PatternBuilder. Although the paper 词性赋码语料库的检索与正则表达式的编写 mentioned two tagging tools, one is CLAWS4 which is not free, the other is treetagger, which do not share the tagset and cannot work together with PatternBuilder. And if no automatic pos tagging tool is available, then PatternBuilder works little.
i'm just a beginner and i'm rather concerned about what kind of automatic pos tagging tools can be used before we use the PatternBuilder. Although the paper 词性赋码语料库的检索与正则表达式的编写 mentioned two tagging tools, one is CLAWS4 which is not free, the other is treetagger, which do not share the tagset and cannot work together with PatternBuilder. And if no automatic pos tagging tool is available, then PatternBuilder works little.
回复: 词性赋码语料库的检索与正则表达式的编写 POS tagged corpus search + regex
PatternBuilder works with both CLAWS C7 tagset and TreeTagger tagset, when different ini or template files are called upon.
CLAWS online trial service allows 10,000 words tagging sercive from an educational site.
http://ucrel.lancs.ac.uk/claws/trial.html
PatternBuilder works with both CLAWS C7 tagset and TreeTagger tagset, when different ini or template files are called upon.
CLAWS online trial service allows 10,000 words tagging sercive from an educational site.
http://ucrel.lancs.ac.uk/claws/trial.html
回复: 词性赋码语料库的检索与正则表达式的编写 POS tagged corpus search + regex
Thank you for your response, prof. Xu!
However, I still wonder what you mean by 'different ini'. Please forgive my ignorance. I mean tagset.ini was created automatically when I first double-clicked the PatternBuilder.exe and how can I get a 'different ini'?
To be more exact, I think Treetagger2 cannot work with PatternBuilder because the regular expression I get with the help of PatternBuilder simply cannot be applied to a text tagged by Treetagger2. Say, '\S+_PPH1\s', the regular expression for the third person singular pronoun 'it' in the PatternBuilder, cannot be found in the text tagged by Treetagger2, which has a different tagset and doesn't include '_PPH1'
Look forward to your reply! Thank you!
Thank you for your response, prof. Xu!
However, I still wonder what you mean by 'different ini'. Please forgive my ignorance. I mean tagset.ini was created automatically when I first double-clicked the PatternBuilder.exe and how can I get a 'different ini'?
To be more exact, I think Treetagger2 cannot work with PatternBuilder because the regular expression I get with the help of PatternBuilder simply cannot be applied to a text tagged by Treetagger2. Say, '\S+_PPH1\s', the regular expression for the third person singular pronoun 'it' in the PatternBuilder, cannot be found in the text tagged by Treetagger2, which has a different tagset and doesn't include '_PPH1'
Look forward to your reply! Thank you!
