求词形还原工具(lemmatiser)

有什么软件可以批量将txt文件进行词形还原(lemma),处理后的文件最好能保留原文件的段落样式,而不是one word per line样式。谢谢!!
TreeTagger软件可以进行词形还原操作,但个人觉得效率比较低,一次只能处理一个txt文件,而且结果为one word per line样式,如附件:
 

附件

  • TreeTagger_lemma.txt
    2.9 KB · 浏览: 93
回复: 求词形还原工具(lemmatiser)

有什么软件可以批量将txt文件进行词形还原(lemma),处理后的文件最好能保留原文件的段落样式,而不是one word per line样式。谢谢!!
TreeTagger软件可以进行词形还原操作,但个人觉得效率比较低,一次只能处理一个txt文件,而且结果为one word per line样式,如附件:

到这里看看,里面可能还有更多的好东东:
CST's Lemmatiser
http://www.cst.dk/online/lemmatiser/uk/index.html
 
回复: 求词形还原工具(lemmatiser)

CST's Lemmatiser 的结果:
Nowadays, in classrooms of school one can often hear someone shouting: "GaoXiao!” But Parents of those who shouts "GaoXiao"may be confused on hearing their sons/daughters uttering this expression. No one knows exactly from when this expression has become popular among young students in China. Literally speaking, "GaoXiao"means creating something funny. But students have given this expression a wider range of meanings. For example, if a student finds something interesting, he/she will say "GaoXiao"to express his/her happiness. If he/she finds something unexpected and surprising, he/she will also say "GaoXiao"to express his/her surprise or depress. What 's more, if a student is playing a joke on another student, the latter may say: Would you please/ you should not ‘GaoXiao'"to convey his/her annoyance. Sometimes, if a student behaves ridiculously, other students will say he is very "GaoXiao. "In a word, "GaoXiao"as a new but popular expression among students, has many meanings and may has even more meanings in the future.

Nowadays/RB/nowadays ,/,/, in/IN/in classrooms/NNS/classroom of/IN/of school/NN/school one/NN/one can/MD/can often/RB/often hear/VB/hear someone/NN/someone shouting/VBG/shout :/:/: "/"/" GaoXiao*MISCNAMEX/NNP/gaoxiao*miscnamex !/./!
"/"/" But=Parents*PERSONNAMEX/NNP/but=parents*personnamex of/IN/of those/DT/those who/WP/who shouts/VBZ/shout "GaoXiao"may/NNP/"gaoxiao"may be/VB/be confused/VBN/confuse on/IN/on hearing/NN/hearing their/PRP$/their sons/daughters/NNS/sons/daughter uttering/VBG/utter this/DT/this expression/NN/expression ././.
No*PERSONNAMEX/NN/no*personnamex one/NN/one knows/VBZ/know exactly/RB/exactly from/IN/from when/WRB/when this/DT/this expression/NN/expression has/VBZ/have become/VBN/become popular/JJ/popular among/IN/among young/JJ/young students/NNS/student in/IN/in China*PERSONNAMEX/NNP/china*personnamex ././.
Literally/RB/literally speaking/VBG/speak ,/,/, "GaoXiao"means/NNPS/"gaoxiao"mean creating/VBG/create something/NN/something funny/JJ/funny ././.
But/CC/but students/NNS/student have/VBP/have given/VBN/give this/DT/this expression/NN/expression a/DT/a wider/JJR/wide range/NN/range of/IN/of meanings/NNS/meaning ././.
For/IN/for example/NN/example ,/,/, if/IN/if a/DT/a student/NN/student finds/VBZ/find something/NN/something interesting/JJ/interesting ,/,/, he/she/NN/he/she will/MD/will say/VB/say "GaoXiao"to/NNP/"gaoxiao"to express/VB/express his/her/NN/his/her happiness/NN/happiness ././.
If/IN/if he/she/NN/he/she finds/VBZ/find something/NN/something unexpected/JJ/unexpected and/CC/and surprising/JJ/surprising ,/,/, he/she/NN/he/she will/MD/will also/RB/also say/VB/say "GaoXiao"to/NNP/"gaoxiao"to express/VB/express his/her/NN/his/her surprise/NN/surprise or/CC/or depress/VB/depress ././.
What/WP/what '/''/' s/JJ/s more/RBR/much ,/,/, if/IN/if a/DT/a student/NN/student is/VBZ/be playing/VBG/play a/DT/a joke/NN/joke on/IN/on another/DT/another student/NN/student ,/,/, the/DT/the latter/NN/latter may/MD/may say/VB/say :/:/: Would/MD/will you/PRP/you please/VB/please //NNP// you/PRP/you should/MD/should not/RB/not '/''/' GaoXiao'"to/NNP/gaoxiao'"to convey/VB/convey his/her/NN/his/her annoyance/NN/annoyance ././.
Sometimes/RB/sometimes ,/,/, if/IN/if a/DT/a student/NN/student behaves/VBZ/behave ridiculously/RB/ridiculously ,/,/, other/JJ/other students/NNS/student will/MD/will say/VB/say he/PRP/he is/VBZ/be very/RB/very "/"/" GaoXiao.*MISCNAMEX/NNP/gaoxiao.*miscnamex "/"/" In*PERSONNAMEX/NNP/in*personnamex a/DT/a word/NN/word ,/,/, "GaoXiao"as/NNP/"gaoxiao"as a/DT/a new/JJ/new but/CC/but popular/JJ/popular expression/NN/expression among/IN/among students/NNS/student ,/,/, has/VBZ/have many/JJ/many meanings/NNS/meaning and/CC/and may/MD/may has/VBZ/have even/RB/even more/JJR/more meanings/NNS/meaning in/IN/in the/DT/the future/NN/future ././.
 
回复: 求词形还原工具(lemmatiser)

非常感谢xusun575的帮助!
CST's online tools功能多样、真是好东东。但美中不足的是,一次只能处理一个文件。
如不勾选“Pos-Tagger”,可得到更简洁的结果:

nowadays , in classroom of school one can often hear someone shout : " gaoxiao !
" but parent of those who shout "gaoxiao"may be confuse on hearing their sons/daughter utter this expression .
no one know exactly from when this expression have become popular among young student in china .
literally speak , "gaoxiao"mean create something funny .
but student have give this expression a wide range of meaning .
for example , if a student find something interesting , he/she will say "gaoxiao"to express his/her happiness .
if he/she find something unexpected and surprising , he/she will also say "gaoxiao"to express his/her surprise or depress .
what ' s much , if a student be play a joke on another student , the latter may say : will you please / you should not ' gaoxiao'"to convey his/her annoyance .
sometimes , if a student behave ridiculously , other student will say he be very " gaoxiao. " in a word , "gaoxiao"as a new but popular expression among student , have many meaning and may have even more meaning in the future .
 
回复: 求词形还原工具(lemmatiser)

非常感谢xusun575的帮助!
CST's online tools功能多样、真是好东东。但美中不足的是,一次只能处理一个文件。
如不勾选“Pos-Tagger”,可得到更简洁的结果:
.......

你的“感激”有内容,好!其一,指出了不足“一次只能处理一个文件”;其二,说出了自己的心得“如不勾选...,可得到更简洁的结果“。
帮助了别人,咱自己也受益,其不善哉?
 
回复: 求词形还原工具(lemmatiser)

……
帮助了别人,咱自己也受益,其不善哉?
哈哈,赞一个“帮助了别人,咱自己也受益,其不善哉?”“予人玫瑰,手有余香(Roses given, fragrance in hand)”,这或许就是帮助的快乐!
 
Back
顶部