Extracting N-ary Cross-sentence Relations using Constrained Subsequence Kernel

TL;DR

This paper introduces a new method for extracting complex, multi-argument, cross-sentence relations within documents, utilizing a novel sequence representation and a constrained subsequence kernel for improved classification.

Contribution

It presents a novel sequence representation and a constrained subsequence kernel for relation extraction spanning multiple sentences with more than two arguments.

Findings

Effective on biomedical and general datasets

Outperforms baseline methods

Handles multi-argument, cross-sentence relations

Abstract

Most of the past work in relation extraction deals with relations occurring within a sentence and having only two entity arguments. We propose a new formulation of the relation extraction task where the relations are more general than intra-sentence relations in the sense that they may span multiple sentences and may have more than two arguments. Moreover, the relations are more specific than corpus-level relations in the sense that their scope is limited only within a document and not valid globally throughout the corpus. We propose a novel sequence representation to characterize instances of such relations. We then explore various classifiers whose features are derived from this sequence representation. For SVM classifier, we design a Constrained Subsequence Kernel which is a variant of Generalized Subsequence Kernel. We evaluate our approach on three datasets across two domains: biomedical and general domain.