Mussa,

ANSWER TO “How can I extract the adjective?”

--------------------------------------------------------------

You can extract adjectives from sentences by applying a parser, or more precisely, a part of speech tagger. Let me use your two sentences as example.

EXAMPLE 1. For the sentence:

“The large photo album has extra charges on delivery.”

1. You apply a parser in order to get the part of speech tags (nouns, verbs, adjectives, etc.) for each word. Suppose that we are applying the Stanford Parser to the above sentence. The parser will output the following:

The/DT large/JJ photo/NN album/NN has/VBZ extra/JJ charges/NNS on/IN delivery/NN

WHERE: JJ stands for adjective, NN stands for noun, VBZ stands for verb, and so on.

2. You extract all the words which have the JJ part of speech tag. For this sentence you extract:

- large/JJ

- extra/JJ

EXAMPLE 2: For the sentence/expression:

“Red car”

1. You apply the parser and you get the following output:

Red/JJ car/NN

2. You extract the words wich have the JJ part of speech tag:

- Red/JJ

PARSERS FOR JAVA:

---------------------------

In Java you can use the following free available parsers for the English language:

- The Stanford Parser: A statistical parser

http://nlp.stanford.edu/software/lex-parser.shtml

- The OpenNLP library

https://opennlp.apache.org/index.html

(This library includes several tools for natural language processing. However you just need the “Part-of-Speech Tagger” for extracting adjectives).

- The TreeTagger

http://www.cis.uni-muenchen.de/~schmid/tools/TreeTagger/

This tagger is not implemented in Java. Therefore if you want to use it from Java you need a wrapper. The tt4j is one of those Java wrappers for the TreeTagger: https://code.google.com/p/tt4j/

All the above links have all the information you need.

I wouldn't consider 'large, big' to be a root for 'size'. It is more that 'size' is the attribute that 'large, big' modifies for 'album' (since that is the head noun). Likewise, 'colour' is the attribute of 'car' that 'red' relates to. Alternatively "large cost" refers to the 'amount' or 'quantity' attribute (ie. a different sense of 'size'). See also "large police force". To recognise this you may need to categorise or classify the headnoun in some way. This may need to be a semantic and/or syntactic category, e.g. mass nouns, tangible objects. Then you can use the category to learn which attributes are most likely to be modified by which adjectives.

As to recognising what is the adjective, as suggested, get a part-of-speech tagger, preferably one that uses a well known tagset like the Penn Treebank set. There are many decent taggers in many forms. Even Eric Brill's old one is still holding up.

Michael

It is ok, now I can get adjective by doing part of speech tagger. The main problem How can I we know the root for (large, big) is size) and the root of red, white and blue is colour. This is main challenge for me now and any help is appreciated .

Not sure for colours, but have a look at Wordnet for other adjectives. The following is what I get when I enter "wn large -attra". Similarly, 'old' gives two senses that are attributes of 'age'

:$ wn large -attra

Attributes of adj large

1 of 7 senses of large

Sense 1

large (vs. small), big (vs. little)

=> size

I do not mean particular adjective but I need general solution for the problem. Colour and size just example to explain the question.

Are Holonyms, Meronyms, Hypernyms and Hyponyms in WordNet could help to find solution for this problem.

You are trying to connect an adjective like "large" to a noun like "size". Holonyms, meronyms, hypernyms and hyponyms are all associations between the same part-of-speech (often a noun). That is why I suggest that you look at the Attributes relationship in Wordnet. To quote from the wngloss manual page:

"attribute: A noun for which adjectives express values. The noun weight is an attribute, for which the adjectives light and heavy express values. "

I have no idea about attributes relationship in Wordnet, could you please recommend me any webpages or text book contain information about attributes relationship in Wordnet.