# Semantic Role Labeling with Associated Memory Network

## TL;DR

This paper introduces a syntax-agnostic semantic role labeling model enhanced by an associated memory network that leverages inter-sentence attention to improve performance, achieving state-of-the-art results on CoNLL-2009.

## Contribution

The novel associated memory network (AMN) effectively utilizes inter-sentence attention and training data as memory to enhance SRL without external resources.

## Key findings

- Achieved state-of-the-art on CoNLL-2009 benchmark datasets.
- Demonstrated effectiveness of inter-sentence attention in SRL.
- Showed that AMN improves dependency-based SRL performance.

## Abstract

Semantic role labeling (SRL) is a task to recognize all the predicate-argument pairs of a sentence, which has been in a performance improvement bottleneck after a series of latest works were presented. This paper proposes a novel syntax-agnostic SRL model enhanced by the proposed associated memory network (AMN), which makes use of inter-sentence attention of label-known associated sentences as a kind of memory to further enhance dependency-based SRL. In detail, we use sentences and their labels from train dataset as an associated memory cue to help label the target sentence. Furthermore, we compare several associated sentences selecting strategies and label merging methods in AMN to find and utilize the label of associated sentences while attending them. By leveraging the attentive memory from known training data, Our full model reaches state-of-the-art on CoNLL-2009 benchmark datasets for syntax-agnostic setting, showing a new effective research line of SRL enhancement other than exploiting external resources such as well pre-trained language models.