Feature Derivation for Exploitation of Distant Annotation via Pattern Induction against Dependency Parses

Abstract

We consider the use of distant supervision for biological information extraction, and introduce two understudied corpora of this form, the Biological Expression Language (BEL) Large Corpus and the Pathway Logic (PL) Datum Corpus. Each resource eschews annotation at the sentence constituent level, and the PL corpus requires synthesis of information across multiple sentences to construct composite knowledge frames. Decomposing this problem into feature induction for slot-level attributes, followed by event assembly over this space of features, we introduce a novel, general-purpose pattern induction procedure, evaluating it against these two corpora, demonstrating its ability to induce effective detection against dependency parses.