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

• URL: http://arxiv.org/abs/2110.07572v1
• Date: Thu, 14 Oct 2021 17:37:04 GMT
• Title: LAGr: Labeling Aligned Graphs for Improving Systematic Generalization in Semantic Parsing
• Authors: Dora Jambor, Dzmitry Bahdanau
• Abstract summary: We show that better systematic generalization can be achieved by producing the meaning representation directly as a graph and not as a sequence. We propose LAGr, the Labeling Aligned Graphs algorithm that produces semantic parses by predicting node and edge labels for a complete multi-layer input-aligned graph.
• Score: 6.846638912020957
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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 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 (MR) directly as a graph and not as a sequence. To this end we propose LAGr, the Labeling Aligned Graphs algorithm that produces semantic parses by 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 an approximate MAP inference procedure. On the COGS and CFQ compositional generalization benchmarks the strongly- and weakly- supervised LAGr algorithms achieve significant improvements upon the baseline seq2seq parsers.

Related papers

• A Flexible, Equivariant Framework for Subgraph GNNs via Graph Products and Graph Coarsening [18.688057947275112]
  Subgraph Graph Neural Networks (Subgraph GNNs) enhance the expressivity of message-passing GNNs by representing graphs as sets of subgraphs. Previous approaches suggested processing only subsets of subgraphs, selected either randomly or via learnable sampling. This paper introduces a new Subgraph GNNs framework to address these issues.
  arXiv  Detail & Related papers  (2024-06-13T16:29:06Z)
• Generative and Contrastive Paradigms Are Complementary for Graph Self-Supervised Learning [56.45977379288308]
  Masked autoencoder (MAE) learns to reconstruct masked graph edges or node features. Contrastive Learning (CL) maximizes the similarity between augmented views of the same graph. We propose graph contrastive masked autoencoder (GCMAE) framework to unify MAE and CL.
  arXiv  Detail & Related papers  (2023-10-24T05:06:06Z)
• Mind the Label Shift of Augmentation-based Graph OOD Generalization [88.32356432272356]
  LiSA exploits textbfLabel-textbfinvariant textbfSubgraphs of the training graphs to construct textbfAugmented environments. LiSA generates diverse augmented environments with a consistent predictive relationship. Experiments on node-level and graph-level OOD benchmarks show that LiSA achieves impressive generalization performance with different GNN backbones.
  arXiv  Detail & Related papers  (2023-03-27T00:08:45Z)
• LAGr: Label Aligned Graphs for Better Systematic Generalization in Semantic Parsing [7.2484012208081205]
  We show that better systematic generalization can be achieved by producing the meaning representation directly as a graph and not as a sequence. We propose LAGr, a general framework to produce semantic parses by independently predicting node and edge labels for a complete multi-layer input-aligned graph. Experiments demonstrate that LAGr achieves significant improvements in systematic generalization upon the baseline seq2seqs in both strongly- and weakly-supervised settings.
  arXiv  Detail & Related papers  (2022-05-19T15:01:37Z)
• Simplifying Node Classification on Heterophilous Graphs with Compatible Label Propagation [6.071760028190454]
  We show that a well-known graph algorithm, Label Propagation, combined with a shallow neural network can achieve comparable performance to GNNs in semi-supervised node classification on graphs with high homophily. In this paper, we show that this approach falls short on graphs with low homophily, where nodes often connect to the nodes of the opposite classes. Our algorithm first learns the class compatibility matrix and then aggregates label predictions using LP algorithm weighted by class compatibilities.
  arXiv  Detail & Related papers  (2022-05-19T08:34:34Z)
• SIGMA: Semantic-complete Graph Matching for Domain Adaptive Object Detection [26.0630601028093]
  Domain Adaptive Object Detection (DAOD) leverages a labeled domain to learn an object detector generalizing to a novel domain free of annotations. Recent advances align class-conditional distributions by narrowing down cross-domain prototypes (class centers) We propose a novel SemantIc-complete Graph MAtching framework for hallucinationD, which completes mismatched semantics and reformulates the adaptation with graph matching.
  arXiv  Detail & Related papers  (2022-03-12T10:14:17Z)
• Reinforcement Learning Based Query Vertex Ordering Model for Subgraph Matching [58.39970828272366]
  Subgraph matching algorithms enumerate all is embeddings of a query graph in a data graph G. matching order plays a critical role in time efficiency of these backtracking based subgraph matching algorithms. In this paper, for the first time we apply the Reinforcement Learning (RL) and Graph Neural Networks (GNNs) techniques to generate the high-quality matching order for subgraph matching algorithms.
  arXiv  Detail & Related papers  (2022-01-25T00:10:03Z)
• cgSpan: Pattern Mining in Conceptual Graphs [0.0]
  Conceptual Graphs (CGs) are a graph-based knowledge representation formalism. In this paper we propose cgSpan a CG frequent pattern mining algorithm. It includes three more kinds of knowledge of the CG formalism: (a) the fixed arity of relation nodes, (b) the signatures, avoiding patterns with concept types more general than the maximal types specified in signatures, and (c) the inference rules, applying them during the pattern mining process.
  arXiv  Detail & Related papers  (2021-10-26T14:28:06Z)
• Joint Graph Learning and Matching for Semantic Feature Correspondence [69.71998282148762]
  We propose a joint emphgraph learning and matching network, named GLAM, to explore reliable graph structures for boosting graph matching. The proposed method is evaluated on three popular visual matching benchmarks (Pascal VOC, Willow Object and SPair-71k) It outperforms previous state-of-the-art graph matching methods by significant margins on all benchmarks.
  arXiv  Detail & Related papers  (2021-09-01T08:24:02Z)
• Learning the Implicit Semantic Representation on Graph-Structured Data [57.670106959061634]
  Existing representation learning methods in graph convolutional networks are mainly designed by describing the neighborhood of each node as a perceptual whole. We propose a Semantic Graph Convolutional Networks (SGCN) that explores the implicit semantics by learning latent semantic-paths in graphs.
  arXiv  Detail & Related papers  (2021-01-16T16:18:43Z)
• Inverse Graph Identification: Can We Identify Node Labels Given Graph Labels? [89.13567439679709]
  Graph Identification (GI) has long been researched in graph learning and is essential in certain applications. This paper defines a novel problem dubbed Inverse Graph Identification (IGI) We propose a simple yet effective method that makes the node-level message passing process using Graph Attention Network (GAT) under the protocol of GI.
  arXiv  Detail & Related papers  (2020-07-12T12:06:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.