Skip to main content

Frontiers of Engineering Reports on Leading-Edge Engineering from the 2011 Symposium (2012) / Chapter Skim
Currently Skimming:

Advancing Natural Language Understanding with Collaboratively Generated Content--Evgeniy Gabrilovich
Pages 55-60

The Chapter Skim interface presents what we've algorithmically identified as the most significant single chunk of text within every page in the chapter.
Select key terms on the right to highlight them within pages of the chapter.


From page 55...
... REPOSITORIES OF COLLABORATIVELY GENERATED CONTENT AS AN ENABLING RESOURCE The unprecedented amounts of information in CGC enable new, knowledgerich approaches to natural language processing, which are significantly more powerful than the conventional word-based methods. Considerable progress has 55
Read the entire page →
From page 56...
... They can also be used to extend existing knowledge repositories, increasing the concept coverage and adding usage examples for pre viously listed concepts. Some CGC repositories, such as Wikipedia, record each and every change to their content, thus making the document authoring process directly observable.
Read the entire page →
From page 57...
... Furthermore, the relationship between those related keywords may be semantic rather than syntactic, and capturing it thus requires access to comprehensive human world knowledge. Previous approaches have attempted to tackle these difficulties by using manually built thesauri, by relying on term co-occurrence data, or by extracting latent word relationships and concepts from a corpus.
Read the entire page →
From page 58...
... In this paper, we showed that the structure and content of these repositories can be used to augment repre sentation of natural language texts with information that cannot be deduced from the input text alone. Using knowledge from CGC repositories leads to double-digit accuracy improvements in a range of tasks, from computing semantic relatedness of words and texts to information retrieval and text classification.
Read the entire page →
From page 59...
... Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Com putational Natural Language Learning, Prague, Czech Republic, June 28–30, 2007. Deerwester, S., S
Read the entire page →

Key Terms

  • natural language
  • computing semantic
  • information retrieval
  • cgc repositories
  • semantic analysis

  • language processing
  • collaboratively generated
  • generated content
  • explicit semantic
  • world knowledge

  • background knowledge
  • using wikipedia
  • using wiktionary
  • relatedness using
  • history analysis

  • named entity
  • revision history
  • entity disambiguation
  • temporal semantic
  • using cgc

  • comprehensive human
  • unprecedented amounts
  • text relatedness
  • proposed revision
  • labor union

  • european conference
  • short text
  • relatedness merely
  • human world
  • czech republic


    • This material may be derived from roughly machine-read images, and so is provided only to facilitate research.
    More information on Chapter Skim is available.