Sagar Sontakke

  • Citations Per Year
Learn More
In this paper, we attempt to solve the problem of Prepositional Phrase (PP) attachments in English. The motivation for the work comes from NLP applications like Machine Translation, for which, getting the correct attachment of prepositions is very crucial. The idea is to correct the PPattachments for a sentence with the help of alignments from parallel data(More)
Delexicalized parsers have been used to directly transfer between languages, producing significantly higher accuracies than unsupervised parsers (McDonald et al., 2006). The authors use a constraint driven learning algorithm where constraints are drawn from parallel corpora to project the final parser. They show that simple methods for introducing multiple(More)
The field of entity extraction has got an immense importance to process this kind of unstructured data. Extracting information from such data is a challenging task and it can be achieved through entity extraction. The way how different entities interact with each other is also an equally imporatant factor to build the knowledge base. The report explains and(More)
  • 1