Questions tagged [dependency-parsing]
92 questions
3
votes
2 answers
Segmenting sentence into subsentences with CoreNLP
I am working on the following problem: I would like to split sentences into subsentences using Stanford CoreNLP. The example sentence could be:
"Richard is working with CoreNLP, but does not really understand what he is doing"
I would now like my…
moritz
- 314
- 2
- 12
3
votes
0 answers
Dependency tree with word, POS tag, relation from CoNLL input
I try to have a dependency tree from CoNLL input using the NLTK DependencyGraph. What I understood is that this class provides a tree() method that build tree structure for dependency without the relation between head and dependents. The tree has no…
David
- 311
- 1
- 4
- 14
3
votes
1 answer
NLP: Determine whether a specific semantic meaning is conveyed in a sentence
I have a collection of sentences from which I would like to extract those that express the following semantic meaning:
I like Italian cuisine.
There are many variations of how such a sentence can be structured and worded. Some examples:
I enjoy…
user3850761
- 31
- 3
3
votes
1 answer
Where can I get CoNLL-X training data?
I'm trying to train the Stanford Neural Network Dependency Parser to check phrase similarity.
The way I tried is:
java edu.stanford.nlp.parser.nndep.DependencyParser -trainFile trainPath -devFile devPath -embedFile wordEmbeddingFile -embeddingSize…
aerin
- 20,607
- 28
- 102
- 140
3
votes
2 answers
Shallow Parsing vs Deep Parsing in Stanford CoreNLP (Java)
I need shallow parsing and deep parsing using Stanford CoreNLP. I have googled a lot but not get succeed. At the end, I found that there are 2 parser, Constituency parser and Dependency parser.
My questions are :
Is Constituency Parser shallow…
iNikkz
- 3,729
- 5
- 29
- 59
2
votes
0 answers
Stanford Stanza -- Dependency Parsing Module -- Output for document with more than one sentence
I have a query about formatting the output of the dependency parsing module when the document to be parsed contains more than one sentence.
One of the examples of using the dependency parsing module in the Stanza manual…
mcr
- 43
- 3
2
votes
1 answer
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 converting code from…
user13530797
- 21
- 3
2
votes
2 answers
How to get spaCy to use universal dependencies
Spacy's site said they use universal dependencies scheme in their annotations specifications page. But when I parse "I love you", '''you''' was made a "dobj" of "love". There's no "dobj" in the universal dependency relations doc. So I have two…
IKnowHowBitcoinWorks
- 329
- 3
- 12
2
votes
1 answer
Converting Spacy generated dependency into CoNLL format cannot handle more than one ROOT?
I used the SpaCy library to generate dependencies and save it into a CoNLL format using the code below.
import pandas as pd
import spacy
df1 = pd.read_csv('cleantweets', encoding='latin1')
df1['tweet'] = df1['tweet'].astype(str)
tweet_list =…
KoKo
- 349
- 5
- 24
2
votes
1 answer
POS tagging not consistent using Spacy en_core_web_lg model
POS tagging for PROPN not working in an expected manner using the en_core_web_lg model.
POS tagging works more predictably using the _md model.
Given the (poorly-formed) sentence:
"CK7, CK-20, GATA 3, PSA, are all negative."
When using the _lg…
Zippy242
- 59
- 4
2
votes
1 answer
Examples where Dependency Parser fails
Can anyone give me few sentences on when the dependency parser fails and why they failed and what is the fix for it?
arkham knight
- 373
- 7
- 18
2
votes
2 answers
Finding whether or not, a word is on the dependency path of two entities with spaCy
I'm working on a nlp problem, given a sentence with two entities I need to generate boolean indicating for each word if it stands on the dependency path between those entities.
For example:
'A misty < e1 >ridge< /e1 > uprises from the < e2 >surge<…
Valentin Macé
- 1,150
- 1
- 10
- 25
2
votes
2 answers
How does a Transition-based Dependency parser decide which operation to do next in its configuration stage?
I understand that the model uses previously trained Part of Speech tagging during its configuration stage. But what if most of the words are new, how would the parser decide its operation then?
Akash
- 395
- 5
- 16
2
votes
0 answers
StanfordDependencyParser returns all labels as NULL in german
I'm trying to get the StanfordDependencyParser in NLTK to run with german.
from nltk.parse.stanford import StanfordDependencyParser
dep_parser = StanfordDependencyParser('../Stanford/stanford-parser-full-2015-12-09/stanford-parser.jar',
…
Denny
- 21
- 1
2
votes
1 answer
Converting output of dependency parsing to tree
I am using Stanford dependency parser and the I get the following output of the sentence
I shot an elephant in my sleep
python dep_parsing.py
[((u'shot', u'VBD'), u'nsubj', (u'I', u'PRP')), ((u'shot', u'VBD'), u'dobj', (u'elephant', u'NN')),…
Riken Shah
- 3,022
- 5
- 29
- 56