56 votes
Accepted

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?

There is no one-to-one correspondence between languages and their vocabularies. This means it is impossible for a computer translator to be invertible. The translator's task going from language A to ...
user avatar
  • 1,484
19 votes
Accepted

A tool to replace all words with antonyms

from nltk.corpus import wordnet try: wordnet.synsets('test') except LookupError: import nltk nltk.download('wordnet') # For more information see: https://www.nltk.org/data.html def ...
user avatar
17 votes

Can we conclude that morpheme is ALWAYS greater than syllable?

In English, one counterexample is the very common '-ed’ (often /d/) ending: ‘filled’ is 1 syllable, and the morphemes are ‘fill’ + ‘-ed’ (/d/).
user avatar
14 votes

Is there a linguistics equivalent to Turing completeness?

In the realm of natural language, the "ideas a language can be used to express" are basically "any": all languages are capable of expressing any idea, so there's only one category of expressive type. ...
user avatar
  • 66.7k
13 votes

Is the way words are used the biggest obstacle in understanding science and technology?

No, you do not have a point, because (good) science does use words accurately and unambiguously. But it is probably true that they don't use the words that you would prefer, or assign the definitions ...
user avatar
  • 66.7k
12 votes
Accepted

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

The figure for entropy of any language will depend on the model we use for computing it. This is quite like how someone who speaks English well would see lesser entropy in English than someone who ...
user avatar
  • 3,487
10 votes

Does lexeme and stem mean the same?

A "lexeme" is a theoretical thing, a unit in the mental lexicon. You can think of it as being an entire dictionary entry, but in our mental knowledge bank of what words mean rather than a ...
user avatar
  • 51k
9 votes

What are the current hurdles to automatic audio to IPA transcription?

Dividing up the audio As you mentioned, formant analysis can place vowels nicely on a chart. But first you have to cut the vowels from the surrounding sounds. Often their formants are changed by ...
user avatar
  • 51k
9 votes

Is there a linguistics equivalent to Turing completeness?

In computer science, one essential property of all Turing-complete languages is that they are able to describe, "in their own way", how they themselves work. For example, you can use a Turing ...
user avatar
  • 191
9 votes
Accepted

Statistical Methods in Etymology

You may want to look at D. Ringe's On Calculating the Factor of Chance in Language Comparison, which lays out some of the problems. I believe that uncontrolled variables are the greatest impediment to ...
user avatar
  • 66.7k
8 votes
Accepted

Conversational English corpus for download

There are many spoken English corpora available. But generally, you need to ask more questions than 'plain text' before you find the right one. Length, level of annotation, format of annotation, type ...
user avatar
8 votes

Are natural languages turing complete?

No, natural languages aren't Turing complete in the same way onions are not. Quoting Wikipedia: A computational system that can compute every Turing-computable function is called Turing-complete (...
user avatar
  • 1,080
8 votes

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

For English there exists a list of Basic OCR corrections by Ted Underwood and Loretta Auvil. In the linked blog they also explain how they generated that list of corrections by simulating typical ...
user avatar
7 votes

Convert audio recording of word to IPA representation

The other answers have hit the highlights, going so far as to suggest that it is impossible in principle. Contrariwise, I argue that it could be done in principle, as long as you don't overstate what ...
user avatar
  • 66.7k
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 ...
user avatar
7 votes

Dataset/Database similar to WALS in Vowel/Phonology

There is the famous UPSID database: http://phonetics.linguistics.ucla.edu/sales/software.htm
user avatar
  • 1,467
7 votes
Accepted

What are the conventions for corpus usage?

I can only speak for Germany, and IANAL (I am not a lawyer). The situation is basically as follows: You can collect material from accessible sources (from the web, from radio broadcasts, from TV) and ...
user avatar
7 votes
Accepted

Where to start if you want to do Chomsky style NLP?

I hadn't heard the term "statistical theory (of language)", but it seems to be a misnomer. I gather from your references that you take some data and use it to estimate the parameters of some ...
user avatar
  • 12.3k
7 votes

Can computational techniques solve historical problems that couldn't otherwise be solved?

You say "... some critics say that these methods have not brought anything new ..." From my recollection of some old results (well outside my areas of expertise), I would say the problem is rather ...
user avatar
  • 12.3k
6 votes
Accepted

Why are functional/logic programming languages like Prolog or Haskell popular with computational linguistics and AI?

Imperative programming languages perform the instructions in the order you specify. Procedural languages (e.g. C) are imperative languages that allow you to group instructions into named blocks called ...
user avatar
  • 1,016
6 votes
Accepted

What is the most comprehensive context-free grammar for English?

The treatment of English worked out in Generalized Phrase Structure Grammar by Gazdar, Klein, Pullum, & Sag is a CFG (with sets of rules given in highly abbreviated form) and is comprehensive in ...
user avatar
  • 12.3k
6 votes

What are the main differences between machine learning and classic approaches to natural language processing problems?

The major dichotomy in NLP is that of rules-based approaches vs statistical approaches. (Machine learning is used in some statistical approaches. Given the timeframe of the development of the field, ...
user avatar
6 votes

Good 10 second explanation of computational linguistics

"Computational linguistics is trying to teach computers to understand ordinary language" would probably make sense to most laypeople. The problem, of course, is that if you tell people something they ...
user avatar
6 votes

What are the current hurdles to automatic audio to IPA transcription?

The most basic problem is that it is impossible (given any realistic i.e. non-Star Trek technology) to map waveforms to IPA letters for an arbitrary language. It is, however, possible for well-enough ...
user avatar
  • 66.7k
6 votes
Accepted

looking for corpus of dialogue recording in appointment between doctors and patients

Contrary to the expectations of some commentators, doctor-patient corpora are available (under some conditions, needing to sign some licence and confidentially agreement) for research. The standard ...
user avatar
6 votes

What language pairs are underserved, and would most benefit from machine-learned bilingual tools?

This question is very important and possible to answer empirically, however, words and concepts do not map 1:1 across languages so the mentioned assumption that bilingual dictionaries will have a ...
user avatar
6 votes

Is author profiling based on gender possible for English?

Certainly! Humans can do this too; computers are just more consistent at it. In general, language usage doesn't just come down to what's grammatical and what's not. A man or a woman can say "I like ...
user avatar
  • 51k
6 votes
Accepted

Is Hebrew a language which can be transliterated programmatically according to a small set of clear rules?

First we have to decide which Hebrew we're talking about. Biblical Hebrew can certainly be transliterated programmatically, since Medieval scribes augmented the writing system to include ...
user avatar
  • 2,208
6 votes

How to find most common expressions starting with "iron"?

Using the Corpus Query Processor or a similar corpus engine with a suitable corpus to answer your question, the query [word="[Ii]ron.*"][word=".*"] and a frequency breakdown on the types does the ...
user avatar
6 votes

Is the way words are used the biggest obstacle in understanding science and technology?

To respond to a few of your specific points: For instance you don't really charge a battery. Battery is full of charges so is everything else. Electrons don't really flow through wires like water ...
user avatar
  • 51k

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