LAGr: Label Aligned Graphs for Better Systematic Generalization in Semantic Parsing
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Semantic ParsingSystematic GeneralizationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
LAGr: Label Aligned Graphs for Better Systematic Generalization in Semantic Parsing
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…
Semantic ParsingSystematic GeneralizationLAGr: Labeling Aligned Graphs for Improving Systematic Generalization in Semantic Parsing
Semantic parsing is the task of producing a structured meaning representation for natural language utterances or questions. Recent research has pointed out that the commonly-used sequence-to-sequence (seq2seq) semantic p…
Semantic ParsingSystematic GeneralizationDistance-Misaligned Training in Graph Transformers and Adaptive Graph-Aware Control
Graph Transformers can mix information globally, but this flexibility also creates failure modes: some tasks require long-range communication while others are better served by local interaction. We study this through a s…
Data-Centric Learning from Unlabeled Graphs with Diffusion Model
Graph property prediction tasks are important and numerous. While each task offers a small size of labeled examples, unlabeled graphs have been collected from various sources and at a large scale. A conventional approach…
DenoisingGraph Property PredictionPredictionProperty Prediction+1Self-Supervised Representation Learning via Latent Graph Prediction
Self-supervised learning (SSL) of graph neural networks is emerging as a promising way of leveraging unlabeled data. Currently, most methods are based on contrastive learning adapted from the image domain, which requires…
Contrastive LearningPredictionRepresentation LearningSelf-Supervised Learning