Trouble information extraction based on a bootstrap approach from Twitter.
Kohei KuriharaKazutaka ShimadaPublished in: PACLIC (2015)
Keyphrases
- information extraction
- social media
- natural language processing
- precision and recall
- online social networks
- social networks
- information retrieval
- text mining
- free text
- micro blogging
- structured data
- social networking
- web documents
- emerging topics
- named entity recognition
- relation extraction
- textual data
- machine translation
- open domain
- machine learning
- semi structured
- conditional random fields
- question answering
- natural language
- semantic tagging
- ontology based information extraction
- relational learning
- user generated content
- named entities
- cross validation
- contingency tables
- public opinion
- hot topics
- data mining
- extracting meaningful
- neural network
- bootstrap sampling
- data sets