English Language & Usage Stack Exchange is a question and answer site for linguists, etymologists, and serious English language enthusiasts. It's 100% free, no registration required.

Sign up
Here's how it works:
  1. Anybody can ask a question
  2. Anybody can answer
  3. The best answers are voted up and rise to the top

This question already has an answer here:

How do I obtain a list of compound words as nouns?

Example: polar bear. I can only detect polar as an adjective and bear as a noun. But polar bear is actually a noun. How do I obtain a free list of such?

Another example is hot dog.

share|improve this question

migrated from stackoverflow.com Feb 4 '13 at 3:08

This question came from our site for professional and enthusiast programmers.

marked as duplicate by RegDwigнt Mar 18 '13 at 22:41

This question has been asked before and already has an answer. If those answers do not fully address your question, please ask a new question.

up vote 1 down vote accepted

Use WordNet. Together with the associated relationship information you can get for WordNet in RDF format you would get the following information for 'polar bear':

white bear of Arctic regions
Synonyms Thalarctos maritimus, Ursus Maritimus, ice bear
--type--> wn30:synset-bear-noun-1
--memberMeronymOf--> wn30:synset-Thalarctos-noun-1

Following the Type relation further would also reveal that it's a Mammal, and an Animal

One way to try Wordnet is on my the demo page for my Natural Language Engine. Simply type 'define' and then the word you want to look up. (P.S. It may take a few seconds to restart if nobody has been there recently.)

share|improve this answer
Ian, thanks for your help. What tool did you use? I used java version of the WordNet library. I can only load nouns,adjs,advs for now...not sure how I detect something like what you did. – nanshi Feb 2 '13 at 9:05
I used the RDF version of WordNet. Parsed that, built an in memory graph, added my own conjugations for verbs, plurals for nouns, ... "polar bear" is in the basic Wordnet files, you just need a parser that can handle the ambiguity that exists throughout the English language. – Ian Mercer Feb 2 '13 at 16:49
Thanks Ian. Which file you used from Wordnet to parse out "polar bear" and "hot dog"? I think I found it from data.noun, but I am not sure if it is. Also, a grep on all the files in 'dict' directory, didn't find "dim sum" – nanshi Feb 7 '13 at 7:25
"wn30:synset-dim_sum-noun-1" is in wordnet-glossary.ttl which is part of the RDF version – Ian Mercer Feb 7 '13 at 7:59
Thanks Ian! I will look into it :) – nanshi Feb 8 '13 at 18:41

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