Stanford NNDep parser: features used

In regards to Stanford’s neural network dependency parser*̦ which features are used during training and testing phases? In practice, which columns in a CONLLᶸˣ formatted data set could be...

CoreNLP tokenizer/sentence splitter misbehaves on HTML input

I'm using the Stanford CoreNLP pipeline from the command line to dependency parse a large document, and it's very important that each line in the document receive its own dependency tree...

French dependency parsing using CoreNLP

I am following the example in this link. I have downloaded the french jar from here. When I call it as follows, java -mx1g -cp "*" edu.stanford.nlp.pipeline.StanfordCoreNLP -props...

Training the SyntaxNet POS Tagger in SytaxNet

I had some difficulties training SyntaxNet POS tagger and parser training and I could find a good solution which I addressed in Answers section. if you have got stuck in one of the following...

How to extract Named Entity + Verb from text

Well, my aim is to extract NE (Person) and a verb connected to it from a text. For example, I have this text: Dumbledore turned and walked back down the street. Harry Potter rolled over inside...

Issues Regarding Training Maltparser Model

I am trying to train a Maltparser Model for Bangla. I have annotated a small Corpus in Conllu Format. But it it gives me null pointer error. So i tried it with some treebank collected from UD...

udpipe_accuracy() always gives the same error " The CoNLL-U line '....' does not contain 10 columns!"

This is regarding the R package udpipe for NLP. I am using it to tokenize, tag, lemmatize and perform dependency parsing on text files. I am not sure which template the conllu file is needed for...

How to save an edited .conllu file using conllu python library

I want to ask something that perhaps I cannot find yet in the internet. First of all I'm using the Universal Dependencies dataset and want to edit some data on Jupyter Notebook (python 3.6). I...

How to obtain enhanced dependency parsing from Stanford NLP tools?

I'm working on a project about dependency parsing for Polish. We’re trying to train the Stanford Neural Network Dependency Parser on data from Polish language (using Universal Dependencies...

How to check whether a word is present into a vector

I am using a vector to retrieve the names of the files into a path. I only want to get a certain type of file. That's why I am trying to use .find to detect if the file has the conllu format. I...

Training custom Swedish spacy model

my intention was to train a custom POS-Tagger and Dependency Parser in spaCy for the swedish language. I followed the instructions on https://spacy.io/usage/training and trained the models on the...

How to generate .conllu from a Doc object?

Where can I find an example .conllu file Spacy will accept ? or example how to generate it ? with IOB ? Trying to convert .conllu file I generated to .json for model training, this way : head_ix...

How to create a TokenList using the conllu library?

I'm trying to create a CoNLL-U file using the conllu library as part of a Universal Dependency tagging project I'm working on. I have a number of sentences in python lists. These contain sub-lists...

How to change text sentence into CoNLL-U format?

I am studying dependency parsing using CoNLL-U format. I can find how to handle CoNLL-U parser or tokenlist, but I cannot find how to convert a text sentence into a CoNLL-U format. I tried...

How to load .conll file in Python?

I tried the three ways below that I found online to read a .conll file in Python but only got error reports that I don't understand. I also read about different types of .conll file, yet I don't...

pip getting killed in Docker

I am building a Docker container based on python:3.7-slim-stretch (same problem also happens on python:3.7-slim-stretch), and it is getting Killed on pip install --no-cache-dir --verbose...

How to change from CoNLL format into a sentences list?

I have a txt file in, theoretically, CoNLL format. Like this: a O nivel B-INDC de O la O columna B-ANAT anterior I-ANAT del I-ANAT acetabulo I-ANAT existiendo O minimos B-INDC cambios...