CODEWITHSUNDEEP
formsparsingnlptext-parsing
Bean Fang
Bean Fang

Reputation: 1

error in applying pre-trained model for english of maltparser

I'm embarking on maltparser. I want to apply the offered

pre-trained model 'engmalt.linear-1.7' to parsing

english sentence on command line.

I download the engmalt and changed its file name from

'engmalt.linear-1.7.zip' to 'engmalt.linear-1.7.mco'. I

save the example english sentence (on engmalt's download page)

in 'infile.conll' and run on command line.

I can't get the result and there's a strange error:

No label symbol available for label 'FORM'.

(By the way, if I test the '/maltparser-

1.7.1/examples/data/talbanken05_test.conll' of maltparser

package,it can surprisingly get the dependency! )

english sentence)?

it mean?

Thanks a lot !

Upvotes: 0

Views: 484

Answers (1)

user4225170
user4225170

Reputation: 21

This is an old question, and I'm not sure the OP still wants an answer. The correct format you should use with the pre-trained model is the ten column format which is defined in this xml:

<?xml version="1.0" encoding="UTF-8"?>
<dataformat name="conllx">
    <column name="ID" category="INPUT" type="INTEGER"/>
    <column name="FORM" category="INPUT" type="STRING"/>
    <column name="LEMMA" category="INPUT" type="STRING"/>
    <column name="CPOSTAG" category="INPUT" type="STRING"/>
    <column name="POSTAG" category="INPUT" type="STRING"/>
    <column name="FEATS" category="INPUT" type="STRING"/>
    <column name="HEAD" category="HEAD" type="INTEGER"/>
    <column name="DEPREL" category="DEPENDENCY_EDGE_LABEL" type="STRING"/>
    <column name="PHEAD" category="IGNORE" type="INTEGER" default="_"/>
    <column name="PDEPREL" category="IGNORE" type="STRING" default="_"/>

</dataformat>

Upvotes: 2

Related Questions