pyBART: Evidence-based Syntactic Transformations for IE
This work addresses a domain-specific issue for NLP practitioners by improving syntactic representations for information extraction, though it is incremental relative to existing Enhanced UD proposals.
The paper tackled the problem of syntactic dependencies lacking explicit semantic relations for information extraction by introducing pyBART, a Python library that transforms Universal Dependency trees into enhanced representations, resulting in higher extraction scores and fewer required patterns in evaluation.
Syntactic dependencies can be predicted with high accuracy, and are useful for both machine-learned and pattern-based information extraction tasks. However, their utility can be improved. These syntactic dependencies are designed to accurately reflect syntactic relations, and they do not make semantic relations explicit. Therefore, these representations lack many explicit connections between content words, that would be useful for downstream applications. Proposals like English Enhanced UD improve the situation by extending universal dependency trees with additional explicit arcs. However, they are not available to Python users, and are also limited in coverage. We introduce a broad-coverage, data-driven and linguistically sound set of transformations, that makes event-structure and many lexical relations explicit. We present pyBART, an easy-to-use open-source Python library for converting English UD trees either to Enhanced UD graphs or to our representation. The library can work as a standalone package or be integrated within a spaCy NLP pipeline. When evaluated in a pattern-based relation extraction scenario, our representation results in higher extraction scores than Enhanced UD, while requiring fewer patterns.