DeepAI AI Chat
Log In Sign Up

A Differentiable Relaxation of Graph Segmentation and Alignment for AMR Parsing

by   Chunchuan Lyu, et al.

Abstract Meaning Representations (AMR) are a broad-coverage semantic formalism which represents sentence meaning as a directed acyclic graph. To train most AMR parsers, one needs to segment the graph into subgraphs and align each such subgraph to a word in a sentence; this is normally done at preprocessing, relying on hand-crafted rules. In contrast, we treat both alignment and segmentation as latent variables in our model and induce them as part of end-to-end training. As marginalizing over the structured latent variables is infeasible, we use the variational autoencoding framework. To ensure end-to-end differentiable optimization, we introduce a continuous differentiable relaxation of the segmentation and alignment problems. We observe that inducing segmentation yields substantial gains over using a `greedy' segmentation heuristic. The performance of our method also approaches that of a model that relies on <cit.>'s segmentation rules, which were hand-crafted to handle individual AMR constructions.


page 1

page 2

page 3

page 4


AMR Parsing as Graph Prediction with Latent Alignment

Abstract meaning representations (AMRs) are broad-coverage sentence-leve...

AMR Alignment: Paying Attention to Cross-Attention

With the surge of Transformer models, many have investigated how attenti...

Relaxed-Responsibility Hierarchical Discrete VAEs

Successfully training Variational Autoencoders (VAEs) with a hierarchy o...

Learned Watershed: End-to-End Learning of Seeded Segmentation

Learned boundary maps are known to outperform hand- crafted ones as a ba...

Structured Reordering for Modeling Latent Alignments in Sequence Transduction

Despite success in many domains, neural models struggle in settings wher...

Incorporating Graph Information in Transformer-based AMR Parsing

Abstract Meaning Representation (AMR) is a Semantic Parsing formalism th...

Semantic Reasoning with Differentiable Graph Transformations

This paper introduces a differentiable semantic reasoner, where rules ar...