Semantic Role Labeling with Associated Memory Network

August 05, 2019 · Entered Twilight · 🏛 North American Chapter of the Association for Computational Linguistics

"Last commit was 6.0 years ago (≥5 year threshold)"

Evidence collected by the PWNC Scanner

Repo contents: README.md, data, data_utils.py, distance, edit_dis.py, final_inter_helper.py, final_model.py, highway.py, inter_utils.py, log, main.py, model, models, preprocess.py, result, scorer.py, snipping, temp

Authors Chaoyu Guan, Yuhao Cheng, Hai Zhao arXiv ID 1908.02367 Category cs.CL: Computation & Language Cross-listed cs.AI, cs.LG Citations 20 Venue North American Chapter of the Association for Computational Linguistics Repository https://github.com/Frozenmad/AMN_SRL ⭐ 11 Last Checked 1 month ago

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.