A Resource-light Approach to Phrase Extraction for English and German Documents from the Patent Domain and User Generated Content.
Julia Maria SchulzDaniela BecksChrista Womser-HackerThomas MandlPublished in: LREC (2012)
Keyphrases
- user generated content
- phrase extraction
- information retrieval
- cross language
- social media
- document collections
- blog posts
- document retrieval
- web documents
- user generated
- information retrieval systems
- relevant documents
- monolingual retrieval
- recommender systems
- relevant content
- user comments
- metadata
- noun phrases
- heuristic rules
- social media content
- machine learning
- hits algorithm
- cross language information retrieval
- cross lingual
- question answering
- co occurrence
- natural language processing