Open language learning for information extraction
EMNLP-CoNLL, pp. 523-534, 2012.
Open Information Extraction (IE) systems extract relational tuples from text, without requiring a pre-specified vocabulary, by identifying relation phrases and associated arguments in arbitrary sentences. However, state-of-the-art Open IE systems such as ReVerb and woe share two important weaknesses -- (1) they extract only relations that...More
PPT (Upload PPT)