7 votes
Accepted

How to detect verb in a sentence where the verb is invisible in the sentence?

This phenomenon is called zero copula. It especially common for third person present tense. I recommend that you read on how this is handled in syntax parsers for Russian or Hindi. It was also an ...
Adam Bittlingmayer's user avatar
7 votes
Accepted

What software is used to make these X-bar trees?

This is almost certainly done with LaTeX, or one of its friends, and the tikz-qtree package. It is an improvement of the qtree package with nicer node placement. If you are not familiar with LaTeX, ...
Keelan's user avatar
  • 4,214
4 votes
Accepted

Can training a Part-of-Speech tagger and parser at the same time improve parsing results?

I think you are talking about joint POS tagging and parsing. If you do not limit yourself to the neural network framework. The following paper can help: graph-based parser: Joint models for Chinese ...
Oneplus's user avatar
  • 101
4 votes
Accepted

Dependency parsing that preserves structural ambiguities?

The top parsers like spaCy, Stanford and Google unfortunately only return one parse, although in many cases another parse is nearly equally probable. However, the always helpful Matt from spaCy ...
Adam Bittlingmayer's user avatar
4 votes
Accepted

What are uses of Dependency Parsing in NLP / Computational Linguistics?

Parsing is mostly an important building block used for improving the performance of downstream tasks, not as an application per se. So, for example, if we are training NER, it helps to hint to the ...
Adam Bittlingmayer's user avatar
3 votes

Split a sentence using nltk and python

If you are familiar with spacy, you can use the dependency of the words in the sentence: import spacy nlp = spacy.load("en_core_web_sm") doc = nlp("Apple is looking at buying U.K. ...
Nour Matta's user avatar
3 votes
Accepted

Convert a non projective dependency tree to a projective one

I've just seen your question, I don't know whether it's still relevant, but here you have a paper that describes how to projectivise a dependency tree. http://www.aclweb.org/anthology/P05-1013
bujol's user avatar
  • 46
3 votes

German Dependency Parsing - question about dependencies between "sich ____ lassen"

Thanks for your question. This example reflects a larger problem in grammaticizing language. Roughly speaking there are two approaches: Generative and descriptive. A parser is generative, presupposing ...
Abas's user avatar
  • 215
3 votes
Accepted

Unable to understand meaning of tag NONE *-1 in Penn Treebank example

After going through a number of examples, I think I got meaning of *NONE* in parse tree output. Let's take an example, suppose we have to parse following sentence: Ricky is a boy and likes fruits. ...
Saurabh Jain's user avatar
3 votes

How far ahead we look when parsing and understanding text

These are more or less like the word-sense disambiguation, anaphora resolution or co-reference resolution examples in the Winograd Schema Challenge and generally in natural language understanding. ...
Adam Bittlingmayer's user avatar
3 votes
Accepted

Parse Tree Formatter Tools?

Here is a script I quickly assembled from pieces of code I had lying around: https://trinket.io/python3/a33a025467?toggleCode=true&showInstructions=true Beware that this script parses your tree ...
Natalie Clarius's user avatar
2 votes

Is there a measure of how easy a sentence is to parse as a Natural Language problem?

Yes, there are measures. Whether they are consistent or useful is subjective. A probabilistic parser like https://demos.explosion.ai/displacy or https://cloud.google.com/natural-language/ returns ...
Adam Bittlingmayer's user avatar
2 votes

Can training a Part-of-Speech tagger and parser at the same time improve parsing results?

Yes, we can train a joint model for POS tagging and dependency parsing. See the paper (and its source code): "A Novel Neural Network Model for Joint POS Tagging and Graph-based Dependency Parsing" ...
NQD's user avatar
  • 121
2 votes

Semantic parsing vs Propositional Representation

Most computational parsing methods yield an output that is a propositional representation within the computer. This includes pure syntactic parsers (if one assumes we can have pure syntax) and ...
peschü's user avatar
  • 251
2 votes

Which one is head noun?

I don't know -- I think it is arguable. It sounds rather peculiar with a plural-agreeing verb: ??One of the lizards are ready to eat. but that might be because the subject, "one of the lizards" ...
Greg Lee's user avatar
  • 12.5k
2 votes

Is it possible to produce a list of syntactic rules for a language?

The answer is yes you can, especially if what you want is a subset of French sentences. You will need more rules for a greater subset. The decision as to when that subset is large enough, is with you. ...
Omar and Lorraine's user avatar
1 vote

Python list to Parse tree

The standard way to make a parse tree using the CYK algorithm is to build a new tree node every time you would be storing "true" in the CYK table, and store that node in the table instead. The node ...
Draconis's user avatar
  • 66.2k
1 vote
Accepted

What do these morphemes' abbreviated glosses mean?

Let's look at the first example blame blame+V+Inf The word form blame is lemmatised as blame, part-of-speech-tagged as verb V and and further anylysed as the infinitive Inf (which includes all of ...
Sir Cornflakes's user avatar
1 vote

Reference work needed for Phrase Markers in English

Per Atamiri's suggestion I found the following papers on Lexical Functional Grammar: Faulk, Yehuda. Lexical-Functional Grammar. http://web.stanford.edu/group/cslipublications/cslipublications/pdf/...
David Farthing's user avatar
1 vote

Semantic parsing vs Propositional Representation

Both entail the compositional process of converting natural language into a formal or machine-interpretable language. I believe the difference is that propositional representation is how some ...
Sonja Pleština's user avatar
1 vote

Automated wh movement for turning an answer into the form of a question

I suggest you look at the account of English wh-expressions given in Generalized Phrase Structure Grammar by Gazdar, Klein, Pullum and Sag. It's very thorough going and explicit. It takes the ...
Greg Lee's user avatar
  • 12.5k
1 vote

What is the name for the phenomenon of verb phrase being an argument of a predicate

In Elements of Symbolic Logic, Hans Reichenbach gives this example of a predicate which is a quantified argument of another predicate: "Napoleon had all the qualities of a great general." This ...
Greg Lee's user avatar
  • 12.5k
1 vote

German Dependency Parsing - question about dependencies between "sich ____ lassen"

Your intuition is correct, the parser is wrong in this case. Note that the argument structure for "lassen" taking an open complement is lassen⟨_,_,P⟨...⟩⟩ where P is the secondary predicator. This ...
Atamiri's user avatar
  • 2,590
1 vote
Accepted

How to interpret the dependency parse tree of an English Slot Grammar?

Your second question is the answer to your first question: The dots indicate the head node of the respecitive phrase. For example, butis the head of the entire sentence, lookis the head of the VP ...
Natalie Clarius's user avatar
1 vote

Parsing and a possible compound verb

Sentences can be conjoined (“I bought a car and Sally sold a goat”), and so can VPs, thus you can say I walked into the bar and saw him I could walk into the bar and see him I picked up the phone and ...
user6726's user avatar
  • 83.1k
1 vote

Parsing and a possible compound verb

Two VPs have been coordinated, "[walk into a bar] and [see whom]', and a relative pronoun has been extracted from the second conjunct. This is an exception to Ross's Coordinate Structure Constraint ...
Greg Lee's user avatar
  • 12.5k
1 vote

Parsing and a possible compound verb

He's the kind of guy SUCH that you could walk into a bar in any part of the country and see (him). I see this as merely the omission of "such" or "of the type that" or even "whereby", and not part of ...
jim H's user avatar
  • 11
1 vote

Representing knowledge extracted from output of dependency parsing

Since you are using CoreNLP to generate dependency trees, a very nice way to tackle your problem would be to use the Tsurgeon library used to manipulate parse trees. Tsurgeon is a (parse) tree ...
Caxton's user avatar
  • 111
1 vote

Can training a Part-of-Speech tagger and parser at the same time improve parsing results?

I can't recall any paper learning a POS tagger and a parser jointly off the top of my head, but the following paper might be of interest to you as they explored multi-task learning (MTL) for parsing, ...
Franck Dernoncourt's user avatar

Only top scored, non community-wiki answers of a minimum length are eligible