Strategies for recognizing proper nouns in NLP

Question

I'm interested in learning more about Natural Language Processing (NLP) and am curious if there are currently any strategies for recognizing proper nouns in a text that aren't based on dictionary recognition? Also, could anyone explain or link to resources that explain the current dictionary-based methods? Who are the authoritative experts on NLP or what are the definitive resources on the subject?

Answer 1

It depends on what you mean by dictionary-based.

For example, one strategy would be to take things that aren't in a dictionary and try to proceed on the assumption that they're proper nouns. If this leads to a sensible parse, consider the assumption provisionally validated and keep going, otherwise conclude that they aren't.

Other ideas:

• In subject position, any simple subject without a determiner is a good candidate.
• Ditto in prepositional phrases
• In any position, the basis of a possessive determiner (e.g. Bob in "Bob's sister") is a good candidate

-- MarkusQ

Answer 2

The task of determining the proper part of speech for a word in a text is called Part of Speech Tagging. The Brill tagger, for example, uses a mixture of dictionary(vocabulary) words and contextual rules. I believe that some of the important initial dictionary words for this task are the stop words. Once you have (mostly correct) parts of speech for your words, you can start building larger structures. This industry-oriented book differentiates between recognizing noun phrases (NPs) and recognizing named entities. About textbooks: Allen's Natural Language Understanding is a good, but a bit dated, book. Foundations of Statistical Natural Language Processing is a nice introduction to statistical NLP. Speech and Language Processing is a bit more rigorous and maybe more authoritative. The Association for Computational Linguistics is a leading scientific community on computational linguistics.

Answer 3

Try searching for "named entity recognition"--that's the term that's used in the NLP literature for this sort of thing.