DeepAI AI Chat
Log In Sign Up

LAGr: Label Aligned Graphs for Better Systematic Generalization in Semantic Parsing

by   Dora Jambor, et al.

Semantic parsing is the task of producing structured meaning representations for natural language sentences. Recent research has pointed out that the commonly-used sequence-to-sequence (seq2seq) semantic parsers struggle to generalize systematically, i.e. to handle examples that require recombining known knowledge in novel settings. In this work, we show that better systematic generalization can be achieved by producing the meaning representation directly as a graph and not as a sequence. To this end we propose LAGr (Label Aligned Graphs), a general framework to produce semantic parses by independently predicting node and edge labels for a complete multi-layer input-aligned graph. The strongly-supervised LAGr algorithm requires aligned graphs as inputs, whereas weakly-supervised LAGr infers alignments for originally unaligned target graphs using approximate maximum-a-posteriori inference. Experiments demonstrate that LAGr achieves significant improvements in systematic generalization upon the baseline seq2seq parsers in both strongly- and weakly-supervised settings.


page 1

page 2

page 3

page 4


LAGr: Labeling Aligned Graphs for Improving Systematic Generalization in Semantic Parsing

Semantic parsing is the task of producing a structured meaning represent...

Measuring Alignment Bias in Neural Seq2Seq Semantic Parsers

Prior to deep learning the semantic parsing community has been intereste...

Weakly-supervised Knowledge Graph Alignment with Adversarial Learning

This paper studies aligning knowledge graphs from different sources or l...

Weakly Supervised Explainable Phrasal Reasoning with Neural Fuzzy Logic

Natural language inference (NLI) aims to determine the logical relations...

Structured Reordering for Modeling Latent Alignments in Sequence Transduction

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

Semantic Graph Parsing with Recurrent Neural Network DAG Grammars

Semantic parses are directed acyclic graphs (DAGs), so semantic parsing ...

Learning Neural Sequence-to-Sequence Models from Weak Feedback with Bipolar Ramp Loss

In many machine learning scenarios, supervision by gold labels is not av...