Explicating the Implicit: Argument Detection Beyond Sentence Boundaries

TL;DR

This paper introduces a novel approach to argument detection that extends beyond sentence boundaries by reformulating it as a textual entailment task, leveraging existing resources to improve performance on document-level benchmarks.

Contribution

It proposes a new method that captures cross-sentence semantic relations without requiring direct supervision, outperforming some supervised methods and language models.

Findings

Outperforms some supervised methods on document-level benchmarks

Does not require direct supervision, leveraging existing NLI and SRL resources

Effectively captures pragmatic relations across sentences

Abstract

Detecting semantic arguments of a predicate word has been conventionally modeled as a sentence-level task. The typical reader, however, perfectly interprets predicate-argument relations in a much wider context than just the sentence where the predicate was evoked. In this work, we reformulate the problem of argument detection through textual entailment to capture semantic relations across sentence boundaries. We propose a method that tests whether some semantic relation can be inferred from a full passage by first encoding it into a simple and standalone proposition and then testing for entailment against the passage. Our method does not require direct supervision, which is generally absent due to dataset scarcity, but instead builds on existing NLI and sentence-level SRL resources. Such a method can potentially explicate pragmatically understood relations into a set of explicit sentences. We demonstrate it on a recent document-level benchmark, outperforming some supervised methods and contemporary language models.