Hierarchical Curriculum Learning for AMR Parsing

10/15/2021
by   Peiyi Wang, et al.
0

Abstract Meaning Representation (AMR) parsing translates sentences to the semantic representation with a hierarchical structure, which is recently empowered by pretrained encoder-decoder models. However, the flat sentence-to-AMR training paradigm impedes the representation learning of concepts and relations in the deeper AMR sub-graph. To make the sequence-to-sequence models better adapt to the inherent AMR structure, we propose a hierarchical curriculum learning (HCL) which consists of (1) structure-level curriculum (SC) and (2) instance-level curriculum (IC). SC switches progressively from shallow to deep AMR sub-graphs while IC transits from easy to hard AMR instances during training. Extensive experiments show that BART trained with HCL achieves the state-of-the-art performance on the AMR-2.0 and AMR-3.0 benchmark, and significantly outperforms baselines on the structure-dependent evaluation metrics and hard instances.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/29/2020

Dialogue Response Selection with Hierarchical Curriculum Learning

We study the learning of a matching model for dialogue response selectio...
research
09/04/2018

Sequence-to-Action: End-to-End Semantic Graph Generation for Semantic Parsing

This paper proposes a neural semantic parsing approach -- Sequence-to-Ac...
research
10/29/2021

Structure-aware Fine-tuning of Sequence-to-sequence Transformers for Transition-based AMR Parsing

Predicting linearized Abstract Meaning Representation (AMR) graphs using...
research
04/19/2022

ATP: AMRize Then Parse! Enhancing AMR Parsing with PseudoAMRs

As Abstract Meaning Representation (AMR) implicitly involves compound se...
research
05/14/2020

DRTS Parsing with Structure-Aware Encoding and Decoding

Discourse representation tree structure (DRTS) parsing is a novel semant...
research
03/20/2021

Token-wise Curriculum Learning for Neural Machine Translation

Existing curriculum learning approaches to Neural Machine Translation (N...
research
11/16/2017

ConvAMR: Abstract meaning representation parsing for legal document

Convolutional neural networks (CNN) have recently achieved remarkable pe...

Please sign up or login with your details

Forgot password? Click here to reset