Questions tagged [parsing]

The process of syntactic analysis, usually used in the context of computational linguistics.

Filter by
Sorted by
Tagged with
18
votes
5answers
3k views

Why is dependency parsing so much faster than constituency parsing?

For example, Cer, Daniel M., et al. "Parsing to Stanford Dependencies: Trade-offs between Speed and Accuracy." LREC. 2010. : Why is dependency parsing so much faster than constituency parsing?
18
votes
2answers
3k views

Is there a favoured data structure for storing ambiguous parse trees in Natural Language Processing?

I know a bit about parsing computer languages. Generally they try to resolve all ambiguities when parsing or abort the parse and throw an error. This means you either got nothing because there was an ...
17
votes
5answers
3k views

Which language would be easiest for a computer to parse?

I have an idea for a programming language that would work more like a spoken language. "sentences" would have an initial context in which specific subjects, verbs, and objects would have meaningful ...
16
votes
2answers
3k views

Is there a well-established metric to measure the effectiveness of a parsing algorithm?

My understanding that 100% accurate parsing (analyzing a text and creating a syntactic tree) is an impossible task for computational linguistics at this moment. However, there are many heuristics or ...
11
votes
3answers
1k views

Can parsing be classified to some complexity class (e.g. NP-complete)?

In computer science (especially computational complexity theory), problems can be classified to some complexity theory. For example, we say the travelling salesman problem belongs to NP-complete. ...
10
votes
2answers
7k views

How is the F1 score computed when assessing dependency parsing?

For example http://naacl2013.naacl.org/Documents/deep-learning-for-nlp-naacl-2013-tutorial.pdf says "+1.4% F1 Dependency Parsing". How is the F1 score computed when comparing dependency-based parse ...
8
votes
2answers
638 views

In what situation a constituency-based tree cannot be constructed from a dependency-based tree?

I am confused regarding the distinction dependency- vs. constituency-based tree: to me they look like they encompass the same information but presented differently. E.g. in the Wikipedia example the ...
7
votes
1answer
748 views

Earley Parser: Ambiguity

I've got a pretty basic question concerning the Earley parser: In case of syntactic ambiguity ( S -> NP VP(V NP(NP PP)) vs. S -> NP VP(VP((V NP) PP) ), are both parses stored in one chart or in two? ...
7
votes
2answers
393 views

German Dependency Parsing - question about dependencies between “sich ____ lassen”

I'm working on project regarding German dependency parsing, and came across something I'm a bit unsure about. Using a parser, when given an input (whether it be in a sentence or just the verbs) which ...
7
votes
1answer
368 views

Representing knowledge extracted from output of dependency parsing

I am working on a problem to represent knowledge extracted from a paragraph and rank it to produce abstractive summaries. I have implemented dependency parsing using Stanford NLP, which gives dot ...
5
votes
4answers
209 views

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

I was wondering if training both a POS tagger and a parser (be it constituency or dependency) at the same time improve the results of parsing in a deep architecture since deep learning can take ...
5
votes
1answer
101 views

How should grammatical errors be treated in parsing and tokenisation?

I'm writing a tokenizer/parser thing to parse & diagram a bunch of sentences gathered from ordinary language use. Most of it parses just fine by following rules, but from time to time there are ...
5
votes
1answer
223 views

How to parse text too variable for formal grammars but too constrained for NLP?

I'm dealing with a corpus of text that is written informally, but generally conforms to a very standard format by convention (think something like Froyo Frozen Yogurt, Smucker's Peanut Butter) and ...
5
votes
2answers
2k views

Is 'It' anaphoric or cataphoric, and what is its antecedent/postcedent?

Question 1a: What does 'It' refer to in the following sentence: It was clearly in the mood to place acknowledgements at the bottom of questions. The context for the above sentence is provided in ...
5
votes
1answer
82 views

What types of errors arise when converting consistency parse trees to dependency parse trees?

I wonder what types of errors arise when automatically converting consistency parse trees to dependency parse trees, and how frequent they are.
5
votes
1answer
387 views

Maltparser vs Freeling for Spanish dependency parser

I need to parse a Spanish corpus with syntactic dependencies. I have tried both Freeling and Maltparser, they both give similar results, but with some divergence. I need the highest accuracy possible, ...
5
votes
1answer
422 views

Performance improvements of using the shift-reduce Stanford Parser

I'm running NLP on large texts, and part of the questions I'm trying to answer have to deal with syntax. I'm using Stanford NLP, including the Stanford Parser. I started out using the probabilistic ...
4
votes
1answer
422 views

Is there a standard corpus against which to benchmark mechanical parsers?

I was wondering if there is a published standard corpus of English sentences which are confounding for mechanical parsers. I am looking over sentences given here, and I have the following (very short) ...
4
votes
2answers
2k views

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

I'm looking for software for illustrating tree diagrams am wondering whether anyone knows which was used to create the one in the post linked below. I have tried messaging the author, but had no ...
4
votes
1answer
824 views

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

Dependency Parsing seems to be present in most of the NLP toolkits out there. What is not clear and what I have trouble finding in Google is what are actual practical, or even research, applications ...
4
votes
1answer
197 views

Dependency parsing that preserves structural ambiguities?

Does a (publicly available) dependency parser exist, that either preserves structural ambiguities in its output or that allows me to generate all possible parse trees for a given input? I am ...
4
votes
1answer
125 views

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

I recently started a new job as an applied linguist engineer and one of the first tasks I was ask to do was to provide a list of syntactic rules that can produce French sentences (for an ...
4
votes
2answers
109 views

Constituency-based parse trees and the word 'both' in noun phrases

I ran into a problem when doing a parse tree recently. It appears to be the word 'both' in the following sentence that is causing the trouble: It is evident for both you and the listener Obviously '...
4
votes
2answers
488 views

Which dependency parsers take auxiliaries to to be heads over content verbs and prepositions to be heads over their complements?

The Universal Stanford Dependencies (USD) parsing scheme subordinates auxiliary verbs to content verbs and prepositions to their complements: http://nlp.stanford.edu/~manning/papers/...
4
votes
1answer
209 views

Dependency Grammar constraints

I study dependency grammar, DG and I have a question regarding constraints of DG. I do understand why do we need constituency grammars, CG and DG, however I don't completely understand the ...
4
votes
1answer
2k views

What part of speech is 'two o'clock' in this sentence? [closed]

I thought adverbs didn't modify nouns but then what's going on in these sentences: It is nearly two o'clock We were there for nearly an hour The town is nearly forty miles from here
4
votes
1answer
226 views

What is the maximum accuracy that can achieve a projective dependency parser in English?

From what I understand: a projective dependency parsers can only output projective tree Wikipedia says: "a large majority of sentences in most languages are projective, i.e. they do not contain ...
4
votes
2answers
690 views

Text parsing: Distinguish between “dictionary words” and names

I have texts in English and German containing "dictionary words" and names. e.g. "... In Florence the painter Leonardo built ..." I have a Java program where need to determine for each word if it ...
3
votes
5answers
153 views

Treebanks that contain both constituency and dependency parse trees

I am looking for treebanks that contain both constituency and dependency parse trees. Both should have been manually annotated (i.e. the dependency parse trees shouldn't have been obtained from the ...
3
votes
3answers
98 views

How far ahead we look when parsing and understanding text

Part of trying to understand how we mentally parse and understand text requires understanding how far ahead we look, which is what this question is about. I'm wondering how we understand how to ...
3
votes
1answer
528 views

What are the major sources of error for state-of-the-art parsers?

I'm especially interested in parsing sentences written in English (dependency or constituency). Ideally I'd like to have an estimation of how much improvement solving each of those major sources of ...
3
votes
1answer
2k views

Stanford parse tree - What does SBAR mean?

I am wondering what SBAR means and how do I correctly represent in a tree this sentence? Why there are 2 S? Original sentence is: After she ate the cake, Emma visited Tony in his room. Thank you! (...
3
votes
1answer
1k views

Which one is head noun?

I am using a parser and I have run into a problem where I am unsure if the syntax tree that it is showing me is correct. The Noun Phrase is: one of the lizards My parser is telling me that "one" ...
3
votes
2answers
87 views

What are the most authoratative references on the notion of shallow parsing?

What are the most authoratative references on the notion of shallow parsing (also known as text chunking) in NLP? I am looking for definitions, examples, and discussion of strings of words that ...
3
votes
1answer
172 views

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

Reading the news report for the AP Twitter hoax: Breaking: Two Explosions in the White House and Barack Obama is injured. I'm thinking this is the most unambiguous and perfect stock market bomb. ...
3
votes
1answer
226 views

What markers can one use to automatically detect a prepositional phrase in an English sentence?

I'm currently working on a project for which I have a need to identify certain aspects of a sentence. What markers can I use to algorithmically detect a prepositional phrase in a sentence? Obviously, ...
3
votes
1answer
692 views

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

I am reading the paper titled Deep parsing in Watson (DOI: 10.1147/JRD.2012.2185409) and need help understanding this figure: This is the paragraph that describes the tree in the figure above: An ...
3
votes
0answers
87 views

How can I calculate the morphological similarity between sentences?

For my bachelor thesis i am probing various text similarity metrics for how much they incorporate different aspects of sentences. To get those aspects I use datasets that are annotated for semantic ...
3
votes
0answers
76 views

What features are good for dependency parsing?

I am trying to implement a graph based dependency parser. Since I come from a computer engineering perspective, I have trouble finding the features. Assuming that we have a (head,dependent) relation ...
3
votes
0answers
50 views

How should “at some time” be tagged in Universal Dependencies framework?

I want to tag a sentence Jones was unemployed at some time before he graduated. with UD tags. I'm not sure how to tag at some time. Stanford parser suggests the reading: case (time-6, at-4) det (...
3
votes
0answers
189 views

Inside-outside algorithm (PCFG learning) and binarization

I am implementing the Inside-outside algorithm to estimate the parameters of a PCFG based on the train corpus. One observation (on existing implementations) is that, the grammar is converted into ...
2
votes
1answer
538 views

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

In case of some Indo-European languages it seems there is no visible verb in the sentence. This is specially visible in languages like Bangla, Hindi etc. For example the sentence Who is there? is ...
2
votes
1answer
134 views

Parse Tree Formatter Tools?

I am looking for tools that can format parse trees. I want to be able to collapse and expand them. I understand that collapsing them is rather simple with regex or even simple search and replace, ...
2
votes
1answer
329 views

Convert a non projective dependency tree to a projective one

I'm trying to build a dependency parser and I want it to construct only projective trees. Do you know any tool that converts Non-projective trees (CONLL-U format) to projective ones?
2
votes
2answers
267 views

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

I am completely naive and new to NLP. I am following a course on NLP on coursera. As I was studying about parse tree, I came across following sentence to parse: Because the CD had an effective yield ...
2
votes
1answer
568 views

Please help me parse the subject complement of

The 2 questions are on the diagram. In question 1 - I emphasize "function as" because my understanding is that (in English) a predicate nominative - even though it can take the form of a preposition ...
2
votes
3answers
209 views

How can you know that a word in a sentence is a verb?

I am wondering what it takes to parse a sentence with incomplete knowledge. That is, take a sentence like this: If I use timeout I have to call again my function at the end of the execution of the ...
2
votes
2answers
255 views

How to derive training data for maltparser classifier from conll file

Could anyone explain how does the maltparser convert the dependency trees from a CONLL file to a series of transitions in order to train its classifier ?
2
votes
1answer
508 views

What's the difference between discontinuity and discontinuous dependencies?

I am reading the Wikpedia page on discontinuities, it says: Worth noting is that a large majority of sentences in most languages are projective, i.e. they do not contain discontinuities. Only ...
2
votes
1answer
42 views

Reference work needed for Phrase Markers in English

I need a thorough online site or downloadable text that goes into detail about English phrase markers as in this example from Beth Levin's Verb Alternations book "This alternation involves verbs found ...