O'Reilly logo

Natural Language Processing with Java and LingPipe Cookbook by Krishna Dayanidhi, Breck Baldwin

Stay ahead with the world's most comprehensive technology and business learning platform.

With Safari, you learn the way you learn best. Get unlimited access to videos, live online training, learning paths, books, tutorials, and more.

Start Free Trial

No credit card required

Named entity coreference with a document

As seen in Chapter 5, Finding Spans in Text – Chunking, LingPipe can use a variety of techniques to recognize proper nouns that correspond to persons, places, things, genes, and so on. However, chunking doesn't quite finish the job, because it doesn't help with finding an entity when two named entities are the same. Being able to say that John Smith is the same entity as Mr. Smith, John or even an exact repeat, John Smith, can be very useful—so useful that the idea was the basis of our company when we were a baby-defense contractor. Our novel contribution was the generation of sentences indexed by what entities they mentioned, which turned out to be an excellent way to summarize what was being said about ...

With Safari, you learn the way you learn best. Get unlimited access to videos, live online training, learning paths, books, interactive tutorials, and more.

Start Free Trial

No credit card required