30

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 would they be?

I'll suggest some points that I think the answers should cover for successfully describing each field in a complete and comprehensive way:

  • What it does and what it is about (also what it's not);
  • Common misconceptions of the field (with consequent debunking);
  • Aims/objective of the field;
  • Tools/instruments and methods adopted by the field;
  • Subfields of each field (if any);
  • Any other points I might have forgotten.
  • 1
    Note: I'm aware that some of these points are available in the Wikipedia articles, but I thought we could elaborate something better. If we deem it necessary we can make a CW answer out of the ones that will come out. Post a comment here if you want to voice your opinion. – Alenanno Apr 16 '12 at 11:24
  • I am addressing this question more concretely in meta as: What is the difference between Computational Linguistics and Natural Language Processing? – babou Dec 2 '14 at 21:17
  • Some time has passed since the original question. For people looking at this question now, I'd say "computational linguistics" certainly encompasses more researches related to humanities, such as historical linguistics. A parallel would be computational approaches employed in sociology or history research, for example - Fundamentally they are still sociology and history nonetheless. "NLP" is much more closely related to computer science. Especially in 2017, NLP is almost exclusively about how deep learning helps with various practical tasks such as speech recognition, machine translation etc. – xji Aug 28 '17 at 13:57
  • This appears to be nothing more than a question about terminology. If you discover some interesting analysis, are you asking which journal you should send your manuscript to? This is not a legitimate linguistic question. – Greg Lee Feb 24 at 21:42
26

I have a PhD in computational linguistics. I can tell you that NLP and CL are not two separate fields. Rather, CL is the superset that encompasses NLP.

In everyday CL practice, NLP focuses on the building of NL parsers and as such it is central to the CL field. CL as a field includes a lot more than NLP. For instance, you can study machine translation, knowledge representation, ontology engineering, text mining, information extraction, etc. all within the CL field. CL is a pretty broad thing and (unlike CS) is not primarily focused on theory. It is highly hands-on. Most theories in CL come from theoretical CS. When it comes to the nitty-gritty CL is the practical application of various algorithms for purposes of natural language processing.

You may occasionally encounter a reference to NLP (sans CL) within the field of CS. This is due to the fact that -originally- the generation of parsers served purposes beyond the confines of natural language (the way we mean "natural language" within CL). So, one could argue that NLP within CS is a slightly different animal than NLP within CL. In essence, it's the same kind of object seen under slightly different light.

| improve this answer | |
  • 2
    Congratulations for your PhD. – babou Dec 2 '14 at 21:14
  • 3
    I don't think as of now (2017) this summary is accurate. NLP is certainly not only about "parsers". It encompasses all kinds of tasks on languages (machine translation, speech recognition etc. etc.), which are performed in a more CS-centric approach, especially deep learning nowadays. – xji Aug 28 '17 at 13:51
  • 1
    I agree with @JIXiang . It appears that NLP has grown to encompass even more of CL, perhaps almost to the extent where they refer to the same thing even more so and only have the "slightly different lighting" to differentiate them now. I say this because most, if not all, examples of CL in this answer are under NLP, at least in academia and research. – prijatelj Jan 24 '18 at 17:53
18

The above answers are all good. I'd like to offer another perspective that I learned while teaching digital libraries that draws on the analogy used in biology:

Computational biology = the study of biology using computational techniques. The goal is to learn new biology, knowledge about living sytems. It is about science.

Bioinformatics = the creation of tools (algorithms, databases) that solve problems. The goal is to build useful tools that work on biological data. It is about engineering.

To make the analogy for any field X, we thus have "Computational X" and "X-omatics". In NLP/CL, NLP is the equivalent of "Linguamatics".

I don't really subscribe to the notion that CL encompasses NLP or vice versa. They both have a purpose. CL studies human language to computationally understand how we as humans have the capacity to produce and understand language. NLP takes a more pragmatic perspective and says that we wish to build systems that facilitate some language interface.

| improve this answer | |
  • 1
    Min-Yen Kan has answered this question! Can't believe! – Andrew Ravus Apr 26 '16 at 9:13
  • 1
    This parallel makes sense. I'd say it's not completely accurate to say "CL studies human language to computationally understand how we as humans have the capacity to produce and understand language." though. That would be describing psycholinguistics. Linguistics is wider than that. For example historical linguistics, which studies the evolution of a language family, is also benefitting a lot from computational approaches. – xji Aug 28 '17 at 13:58
  • I find @xji is extremely correct in highlighting why the parallel isn't at all as tight. I'd still tend to concur that this kind of partition could have made sense as a good resort even despite its flaw that he brings up here :-) – Matan Dec 27 '18 at 11:47
13

The difference is that Computational Linguistics tends more towards Linguistics, and answers linguistic questions using computational tools. Natural Language Processing involves applications that process language and tends more towards Computer Science.

However, the distinction between the two terms is fading and they are being used more and more interchangeably.

| improve this answer | |
  • 1
    While I agree some with @anogal, as a PhD student in Computational Linguistics I would agree most with this answer. My advisor would say they are interchangable, but i call myself CL because it somehow sounds sexier than NLP. Seriously though, why I really call myself CL is because I came to the field because of my love for linguistics and not for my love of Computer Science. I would strongly advocate for this distinction though not all would agree. – demongolem Dec 20 '12 at 16:09
3

The terms are often used interchangeably. More often than not*, NLP is used when there is actual processing involved, rather than abstract theoretical topics. Comprehensive websites such as ACL wiki page write both separately, or combine them into CL/NLP or NLP/CL.

* - just my impression

Perhaps Computational Psycholinguistics is part of Computational Linguistics, but not a part of Natural Language Processing.

| improve this answer | |
  • 2
    Corpus linguistics is also sometimes counted as part of comp. ling., but I've never heard it included under NLP. Basically, if the goal is to build a better X (where X could be "tagger," "parser," "machine translator," "OCR system," etc.) then it's NLP. If the goal is just to gather data that's relevant to some question in theoretical linguistics, and you're not doing anything to improve the existing computational tools, then it's not NLP, but it might still be comp. ling. if you're using a computer as an essential part of the project. – Leah Velleman Apr 17 '12 at 2:06
3

Some time has passed since the original question. For people looking at this question now, I'd say "Computational Linguistics" certainly encompasses more researches related to humanities, such as historical linguistics. A parallel would be the computational approaches employed in sociology or history research - Fundamentally they are still sociology and history nonetheless. "NLP" is much more closely related to computer science. Especially now in 2017, NLP is almost exclusively about how deep learning helps with various practical tasks such as speech recognition, machine translation etc.

Another illustration of the matter would be that NLP is mostly a research direction under various Computer Science departments, especially in the US, while many "Computational Linguistics" research is actually under the Linguistic department/Philosophy faculty and the degree program confers a Bachelor of Arts degree, especially in many European universities.

Of course the boundary might not be that clear and many universities which offer Computational Linguistics degrees have long been involved in more "NLP-esque" aspects of research as well and have been hiring professors with CS background. But the above generalization still applies.

| improve this answer | |
1

A parts of the Linguistics community considers "Computational Linguistics" to have a very narrow scope about how the human brain computes during the processing of language, what are the limits of this processing, and how can we create tests that measure these limits of the human brain. Sometimes this involves computer simulation to test a theory. This community would say that Artificial Intelligence that uses computers to process language should be called "Computer Linguistics" or "Natural Language Processing".

The mainstream point of view, however, is the one already given in previous answers: "Computational Linguistics" is the same as "Computer Linguistics" and contain "Natural Language Processing", with the difference that the latter operates on a much more shallow representational level than the former.

| improve this answer | |
  • I wouldn't say it's "on a much more shallow representational level"... That makes little sense. How "deep" is Chomskian grammar, which is already much debunked, for example, compared with very complicated neural networks run on a cluster of machines? They are just in many cases different research areas with different focuses. – xji Aug 28 '17 at 14:01

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.