Semantic Role Labeling with Iterative Structure Refinement

TL;DR

This paper introduces an iterative refinement approach for Semantic Role Labeling that models interdependent argument decisions, leading to improved performance across multiple languages.

Contribution

It proposes a novel iterative refinement method with a restricted network architecture to effectively model argument interactions in SRL.

Findings

Outperforms baseline models on all 7 CoNLL-2009 languages

Achieves state-of-the-art results on 5 languages, including English

Demonstrates the effectiveness of modeling argument interactions through iterative refinement

Abstract

Modern state-of-the-art Semantic Role Labeling (SRL) methods rely on expressive sentence encoders (e.g., multi-layer LSTMs) but tend to model only local (if any) interactions between individual argument labeling decisions. This contrasts with earlier work and also with the intuition that the labels of individual arguments are strongly interdependent. We model interactions between argument labeling decisions through {\it iterative refinement}. Starting with an output produced by a factorized model, we iteratively refine it using a refinement network. Instead of modeling arbitrary interactions among roles and words, we encode prior knowledge about the SRL problem by designing a restricted network architecture capturing non-local interactions. This modeling choice prevents overfitting and results in an effective model, outperforming strong factorized baseline models on all 7 CoNLL-2009 languages, and achieving state-of-the-art results on 5 of them, including English.