Skip to main content

Questions tagged [computational-linguistics]

A branch of science that uses computers and mathematical methods to construct and investigate linguistic theory. Its technological and algorithmic implementation is called NLP.

Filter by
Sorted by
Tagged with
33 votes
6 answers
19k views

What are the fundamental differences between Natural Language Processing and Computational Linguistics?

I have a vague knowledge regarding those two fields, but I admit there are some fundamental concepts that I lack. So, if we had to write down the actual differences between these two fields, what ...
Alenanno's user avatar
  • 9,428
30 votes
3 answers
7k views

Why don't you get back the original text when you use translation software to translate something into another language and then back into English?

I translated "How to use Web?" into some other language using machine translation, but after I translated the result back into English, it is not the same as the first text I put into the translator. ...
new Q Open Wid's user avatar
25 votes
7 answers
23k views

Convert audio recording of word to IPA representation

Are the any open source tools/software libraries to convert an audio clip to its IPA representation? If so, are they accurate? If not, why not? Here is a Gaelic word I wish to convert: Ogg format: ...
Baz's user avatar
  • 1,082
25 votes
5 answers
652 views

What has NLP/CL brought to the table of pencil-and-paper linguistics?

What role do NLP (natural language processing) and/or CL (Computational linguistics) play in today's theoretical linguistics? Does, for instance, computability and formal specification play a big ...
user avatar
24 votes
4 answers
4k views

Is there a linguistics equivalent to Turing completeness?

In computer science, programming languages can be described in terms of "Turing completeness", basically, whether a programming language is capable of expressing any* algorithm. A non-Turing-complete ...
TheEnvironmentalist's user avatar
18 votes
7 answers
6k views

Looking for a good beginners reference to learn computational linguistics

Recently in my work I came across the Backus–Naur Form (BNF), one way of describing a context-free grammar. Since then, I've been interested in learning how to deconstruct and parse not only computing ...
Hooked's user avatar
  • 517
18 votes
2 answers
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 ...
hippietrail's user avatar
  • 14.7k
18 votes
1 answer
13k views

What do WordNet::Similarity scores mean?

I am using WordNet Interface in NLTK, which facilitates computation of a number of similarity metrics: Path similarity Leacock-Chodorow Similarity Wu-Palmer Similarity Resnik Similarity Jiang-Conrath ...
piggs_boson's user avatar
17 votes
4 answers
42k views

Automated French/Italian/German to IPA transcription

I'm looking for a website or software that will take text written in a source language and produce a transcription in IPA. The languages I am interested in are French, Italian and German, but if you ...
Robin's user avatar
  • 273
17 votes
5 answers
4k 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 ...
Oggy Transfluxitor Jones's user avatar
16 votes
3 answers
1k views

Is there practical application of X' theory in natural language processing?

I was taught X' theory in generative grammar lectures, only to find out that NLP uses mainly simpler grammars, such as HPSG or statistical models such as hidden Markov models. Is X' of any use for ...
Evpok's user avatar
  • 870
16 votes
2 answers
4k 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 ...
Louis Rhys's user avatar
  • 8,541
15 votes
2 answers
9k views

Automatically Converting Natural Language to First-Order Logic

I'm trying to find a way to automatically convert arbitrary natural language sentences into first-order logic predicates. Although complex, this seems to be feasible to me, through inverse lambda ...
izilotti's user avatar
  • 261
14 votes
2 answers
6k views

What does a computational linguist actually do?

Currently, I working on my application for the Bachelor of Philosophy program at Penn State to major in cognitive linguistics, but at I am also a computer science major, my advisor wants me to ...
Nick Anderegg's user avatar
14 votes
4 answers
6k views

Are there natural languages that do not obey Zipf's law?

Is there a natural language which is known not to follow Zipf's law? I'm interested to see if it's really universal. This is what Zipf's law states: Zipf's law states that given some corpus of ...
sashoalm's user avatar
  • 510
14 votes
2 answers
538 views

How do computational linguists abstractly represent a language?

When building models of the evolution of languages or similar phenomena where many different languages are involved and change over time, how do computational linguists abstractly model a language? ...
Artem Kaznatcheev's user avatar
13 votes
3 answers
346 views

How do purely statistical machine translators deal with different word orders?

Even relatively closely related languages can differ greatly in word order. Take English and German for instance. English is pretty boringly subject-verb-object whereas in German the finite verb must ...
hippietrail's user avatar
  • 14.7k
13 votes
1 answer
772 views

Automatic phonetic transcription of speech: is it still a difficult problem?

A friend was asking me why there aren't any programs that can analyze a user's pronunciation of words and then give feedback/suggestions. Indeed, given an accurate phonetic transcription of a ...
Animadvert's user avatar
12 votes
2 answers
3k views

What is the entropy per word of random yet grammatical text?

It has been suggested that to construct an uncrackable yet memorable passphrase with 256-bits of entropy, the passphrase should be manifested as a poem. The answerer made an estimation of the entropy ...
user avatar
12 votes
1 answer
647 views

What are some resources that I can use to gather Twitter data for an NLP project?

I was going to use the Edinburgh Twitter Corpus that is referenced in this paper: The Edinburgh Twitter Corpus. But apparently Twitter has changed their Terms and the corpus is no longer available. ...
Mark Tuttle's user avatar
12 votes
2 answers
704 views

Bar-Hillel's critique of machine translation 50 years later

More than fifty years ago, philosopher Yehoshua Bar-Hillel wrote wrote an influential paper about computerized translation entitled: A Demonstration of the Nonfeasibility of Fully Automatic High ...
Gil Kalai's user avatar
  • 317
12 votes
4 answers
4k views

Is there free and open Chinese corpus?

The corpus in NLTK sinica can be used for research. There are two shortcomings for sinica to be used in research. too small it is a traditional Chinese corpus Can someone here introduce a big and ...
showkey's user avatar
  • 223
12 votes
2 answers
449 views

If the Rosetta stone were to be translated today, would the process be the same as used the first time?

Are there any techniques available today that would make it considerably easier to anyone attempting to translate it today (as if they were trying todo it for the first time)? Otherwise would the ...
jimjim's user avatar
  • 221
12 votes
4 answers
594 views

Best method for building a learner corpus for DDL

I'm looking for a set of free and (somewhat) easy tools that I can use with my EFL writing students next semester. I want to analyze their initial essays and look for common errors that can be ...
Acornrevolution's user avatar
11 votes
3 answers
2k views

Efficient linguistic algorithms for detecting language of a website?

Some browser addons and web-services for website/dictionary translation sometimes offer a "automatic-language-detection" feature. This works more or less in my experience. There is probably a variety ...
Hauser's user avatar
  • 612
11 votes
2 answers
785 views

How to best clean a large historical corpus ridden with OCR errors

Overview: I have a very large corpus of historical news papers (17th-20th cent.). The word count is about 20 bln. It's raw OCR-ed data in txt-files of about 150 GB. One newspaper issue per file (some ...
Mat's user avatar
  • 231
11 votes
2 answers
4k views

Are there sentence boundary disambiguation algorithms which can handle punctuation errors with decent accuracy?

Most algorithms for splitting text into sentences which I've found rely on punctuation being correct. However, in many real world applications, there will be substantial numbers of punctuation errors (...
Alexey Romanov's user avatar
11 votes
1 answer
703 views

The power of trigram language models (2nd order Markov models)

Many people in computational linguistics seem to mention the unexpected power of trigram (or 2nd order Markov) models for language modeling. For instance, it has been stated (verbally) to me on ...
Julie's user avatar
  • 377
10 votes
3 answers
11k views

How to test if a string of words is a grammatical sentence

Is there a way to test to see if a string of words forms a complete sentence? For example: The dog jumped over the fence == Good The cat square seven the triangle == BAD I was thinking the type ...
Steven Smethurst's user avatar
10 votes
6 answers
516 views

Does the P versus NP conjecture in computer science have any direct relevance to linguistics?

From Wikipedia: The P versus NP problem is a major unsolved problem in computer science. Informally, it asks whether every problem whose solution can be quickly verified by a computer can also be ...
EsperantoSpeaker1's user avatar
10 votes
1 answer
5k views

How to identify character names in a body of text?

I'm trying to research methods of identifying or pattern matching names of characters in a novel or a general body of text, but so far my search has been unsuccessful, since "character" refers to ...
Aram Kocharyan's user avatar
10 votes
1 answer
2k views

Automatic/Computational Language Detection in Speech

Are there any packages that do much the same thing for audio/speech that the langid component/corpus of NLTK does for written text? The langid corpus/tool makes surprisingly accurate guesses about a ...
chbrown's user avatar
  • 213
10 votes
2 answers
471 views

Are linguistic corpora under threat from AI-generated text?

As many will be aware, there has been a lot of concern about the spread of AI generated text posted on the Stack Exchange network, leading to moderators on several sites standing down. See here and ...
Araucaria - him's user avatar
10 votes
1 answer
298 views

What statistical methods are used to test whether a corpus of symbols is linguistic?

In their 2009 paper on the Indus Script, Rao et al. describe a test for deciding whether a corpus of symbols is in fact a collection of texts in some language. Over-simplifying a bit, the approach ...
Azo's user avatar
  • 293
10 votes
3 answers
2k 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. ...
Louis Rhys's user avatar
  • 8,541
10 votes
1 answer
212 views

Linguistic research on translation evaluation

I have a background in natural language processing and machine translation, and recently I've been interested in automatic evaluation of translations. I've read a lot of literature from the machine ...
Sara's user avatar
  • 181
9 votes
2 answers
3k views

Is there a list of word meanings that are universally represented in all languages?

I am looking for a comprehensive list of words/concepts that are represented in most if not all known languages - presumably the category would include human body parts (hand, foot, mouth, eye), ...
norlesh's user avatar
  • 221
9 votes
6 answers
3k views

Is there a branch of linguistics using Calculus as a mathematical tool?

Is there a branch of linguistics using Calculus as a mathematical tool? I mean, can we use differential or integrate in linguistic study?
Ave Maleficum's user avatar
9 votes
3 answers
878 views

Mathematical preparation for postgraduate studies in Linguistics

I posted this question in https://math.stackexchange.com/ and it was suggested to me that it would be a good idea to submit the question here, too, as there might be more specialists on the matter. I ...
Orest Xherija's user avatar
9 votes
3 answers
9k views

Non-Projective Example

I'm looking for an example sentence with a non-projective dependency parse. It doesn't have to be in English, though such an example would be nice.
Omer's user avatar
  • 99
9 votes
2 answers
2k views

Are there any statistics or web services for n-grams of frequent English words?

I found this for six common subjects. But it doesn't contain the complete statistics about all common English words.
ARZ's user avatar
  • 233
9 votes
1 answer
610 views

What is the Relationship Between Document Length and Unique Words

Sorry if my question is a little more mathematical in nature, but my question is: Suppose I took a document of some length whether it be news article, book, or something of that sort. What sort of ...
demongolem's user avatar
9 votes
2 answers
1k views

IDE for context free grammars for natural languages?

Is there any such thing as a Integrated Development Environment for context free grammars (or any variant on a formal, machine parsable grammar) that target natural languages? The ones for BNF ...
MatthewMartin's user avatar
9 votes
3 answers
3k views

What's the real need for an end-symbol in n-gram models?

There's a footnote in Jurafsky & Martin (2008, p.89) pointing out that, without an end-symbol, an n-gram model would not be "a true probability distribution". Even after seeking the paper they've ...
mcrisc's user avatar
  • 191

1
2 3 4 5
14