1

I am looking for some resources pertaining to the parsing and understanding of English (or just human language in general). While this is obviously a fairly complicated and wide field of study, I was wondering if anyone had any book or internet recommendations for study of the subject. I am aware of the basics, such as searching for copulas to draw word relationships, but anything you guys recommend I will be sure to thoroughly read.

Thanks.

lethalman
  • 1,976
  • 1
  • 14
  • 18
beta
  • 647
  • 5
  • 19

4 Answers4

1

Check out WordNet.

Noon Silk
  • 54,084
  • 6
  • 88
  • 105
  • @z5h: Actually, it does help with "parsing and understanding" precisely because it *is* a database (i.e. definitions) of what is what. When you know what is what, you can make decisions about it, and hence "understand" it. – Noon Silk Feb 26 '10 at 04:31
  • I understand. But it's kind of like pointing someone who wants to learn English to a Dictionary. In theory it's all they need. In practice, the Dictionary alone will not get them anywhere. I commented because you were awarded the "correct" answer, and I felt your response was not complete. Anyone reading SO will now be aware of that. I did not up/downvote. – Mark Bolusmjak Feb 26 '10 at 04:46
1

You probably want a book like "Representation and Inference for Natural Language - A First Course in Computational Semantics"

http://homepages.inf.ed.ac.uk/jbos/comsem/book1.html

Mark Bolusmjak
  • 23,606
  • 10
  • 74
  • 129
0

Another way is looking at existing tools that already do the job on the basis of research papers: http://nlp.stanford.edu/index.shtml I've used this tool once, and it's very nice. There's even an online version that lets you parse English and draws dependency trees and so on. So you can start taking a look at their papers or the code itself.

Anyway take in consideration that in any field, what you get from such generic tools is almost always not what you want. In the sense that the semantics attributed by such tools is not what you would expect. For most cases, given a specific constrained domain it's preferable to roll your own parser, and do your best to avoid any ambiguities beforehand.

lethalman
  • 1,976
  • 1
  • 14
  • 18
0

The process that you describe is called natural language understanding. There are various algorithms and software tools that have been developed for this purpose.

Community
  • 1
  • 1
Anderson Green
  • 30,230
  • 67
  • 195
  • 328