Relation extraction via one-shot dependency parsing on intersentential, higher-order, and nested relations

Abstract

: Despite the emergence of digitalization, people still interact with institutions via traditional means such assubmitting free formatted petitions, orders, or applications. These noisy documents generally consist of complex relationsthat are nested, higher-order, and intersentential. Most of the current approaches address extraction of only sentencelevel and binary relations from grammatically correct text and generally require high-level linguistic features coming frompreprocessors such as a parts-of-speech tagger, chunker, or syntactic parser. In this article, we focus on extracting complexrelations in order to automate the task of understanding user intentions. We propose a novel language-agnostic and noiseimmune approach that does not require preprocessing of input text. Unlike previous literature that uses dependencyparsing outputs as input features, we formulate the relation extraction task directly as a one-shot dependency parsingproblem. The presented method was evaluated using a representative dataset from the banking domain and obtained91.84% labeled attachment score (LAS), which provides an improvement of 42.85 percentage points over a rule-basedbaseline.