Semantic Role Labeling with Associated Memory Network
This addresses the problem of improving SRL accuracy for NLP researchers and practitioners, offering a novel approach beyond external resources like pre-trained language models, though it is incremental as it builds on existing dependency-based methods.
The paper tackles the performance bottleneck in semantic role labeling (SRL) by proposing a syntax-agnostic model enhanced with an associated memory network (AMN), which uses inter-sentence attention from labeled training data to improve dependency-based SRL, achieving state-of-the-art results on the CoNLL-2009 benchmark datasets.
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.