Created
January 28, 2020 13:26
-
-
Save reality/8871727f65b26c35f9880c6ad43284c1 to your computer and use it in GitHub Desktop.
some example code to lemmatise a directory of text documents using stanford corenlp
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env groovy | |
@Grab(group='commons-cli', module='commons-cli', version='1.4') | |
@Grab(group='org.apache.commons', module='commons-lang3', version='3.4') | |
@Grab(group='edu.stanford.nlp', module='stanford-corenlp', version='3.7.0') | |
@Grab(group='edu.stanford.nlp', module='stanford-corenlp', version='3.7.0', classifier='models') | |
@Grab(group='edu.stanford.nlp', module='stanford-parser', version='3.7.0') | |
import java.util.concurrent.* | |
import java.util.concurrent.atomic.* | |
import groovyx.gpars.* | |
import org.codehaus.gpars.* | |
import edu.stanford.nlp.pipeline.* | |
import edu.stanford.nlp.ling.* | |
import edu.stanford.nlp.semgraph.* | |
def props = new Properties() | |
props.put("annotators", "tokenize, ssplit, pos, lemma") | |
StanfordCoreNLP pipeline = new StanfordCoreNLP(props) | |
def files = [] | |
new File('./texts').eachFile { files << it } | |
def i = 0 | |
GParsPool.withPool(85) { p -> // he he he | |
files.eachParallel{ e -> | |
def text = e.text | |
text = text.replaceAll('\n\n', '.\n') | |
text = text.replaceAll('\u2022', '. ') | |
text = text.replaceAll('–', '. ') | |
text = text.replaceAll('-', '. ') | |
text = text.replaceAll('– ', '. ') | |
text = text.replaceAll('\\s+', ' ') | |
text = text.replaceAll(', \\?', '. ?') | |
text = text.replaceAll('\\.', '. ') | |
def aDocument = new Annotation(text.toLowerCase()) | |
pipeline.annotate(aDocument) | |
def newText = '' | |
aDocument.get(CoreAnnotations.SentencesAnnotation.class).each { sentence -> | |
newText += sentence.get(CoreAnnotations.TokensAnnotation.class).collect { | |
it.lemma() | |
}.join(' ') + ' ' | |
} | |
newText = newText.replaceAll(' ,', ',') | |
newText = newText.replaceAll(' \\.', '.') | |
new File('new_texts/' + e.getName()).text = newText | |
println "${++i}/${files.size()}" | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment