AMRs Assemble! Learning to Ensemble with Autoregressive Models for AMR Parsing

• URL: http://arxiv.org/abs/2306.10786v1
• Date: Mon, 19 Jun 2023 08:58:47 GMT
• Title: AMRs Assemble! Learning to Ensemble with Autoregressive Models for AMR Parsing
• Authors: Abelardo Carlos Mart\'inez Lorenzo, Pere-Llu\'is Huguet Cabot, Roberto Navigli
• Abstract summary: We show how ensemble models can exploit SMATCH metric weaknesses to obtain higher scores, but sometimes result in corrupted graphs. We propose two novel ensemble strategies based on Transformer models, improving robustness to structural constraints, while also reducing computational time.
• Score: 38.731641198934646
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: In this paper, we examine the current state-of-the-art in AMR parsing, which relies on ensemble strategies by merging multiple graph predictions. Our analysis reveals that the present models often violate AMR structural constraints. To address this issue, we develop a validation method, and show how ensemble models can exploit SMATCH metric weaknesses to obtain higher scores, but sometimes result in corrupted graphs. Additionally, we highlight the demanding need to compute the SMATCH score among all possible predictions. To overcome these challenges, we propose two novel ensemble strategies based on Transformer models, improving robustness to structural constraints, while also reducing the computational time. Our methods provide new insights for enhancing AMR parsers and metrics. Our code is available at \href{https://www.github.com/babelscape/AMRs-Assemble}{github.com/babelscape/AMRs-Assemble}.

Related papers

• AMR Parsing with Causal Hierarchical Attention and Pointers [54.382865897298046]
  We introduce new target forms of AMR parsing and a novel model, CHAP, which is equipped with causal hierarchical attention and the pointer mechanism. Experiments show that our model outperforms baseline models on four out of five benchmarks in the setting of no additional data.
  arXiv  Detail & Related papers  (2023-10-18T13:44:26Z)
• An AMR-based Link Prediction Approach for Document-level Event Argument Extraction [51.77733454436013]
  Recent works have introduced Abstract Meaning Representation (AMR) for Document-level Event Argument Extraction (Doc-level EAE) This work reformulates EAE as a link prediction problem on AMR graphs. We propose a novel graph structure, Tailored AMR Graph (TAG), which compresses less informative subgraphs and edge types, integrates span information, and highlights surrounding events in the same document.
  arXiv  Detail & Related papers  (2023-05-30T16:07:48Z)
• Federated Learning Aggregation: New Robust Algorithms with Guarantees [63.96013144017572]
  Federated learning has been recently proposed for distributed model training at the edge. This paper presents a complete general mathematical convergence analysis to evaluate aggregation strategies in a federated learning framework. We derive novel aggregation algorithms which are able to modify their model architecture by differentiating client contributions according to the value of their losses.
  arXiv  Detail & Related papers  (2022-05-22T16:37:53Z)
• Hierarchical Memory Learning for Fine-Grained Scene Graph Generation [49.39355372599507]
  This paper proposes a novel Hierarchical Memory Learning (HML) framework to learn the model from simple to complex. After the autonomous partition of coarse and fine predicates, the model is first trained on the coarse predicates and then learns the fine predicates.
  arXiv  Detail & Related papers  (2022-03-14T08:01:14Z)
• Ensembling Graph Predictions for AMR Parsing [28.625065956013778]
  In many machine learning tasks, models are trained to predict structure data such as graphs. In this work, we formalize this problem as mining the largest graph that is the most supported by a collection of graph predictions. We show that the proposed approach can combine the strength of state-of-the-art AMRs to create new predictions that are more accurate than any individual models in five standard benchmark datasets.
  arXiv  Detail & Related papers  (2021-10-18T09:35:39Z)
• Probabilistic, Structure-Aware Algorithms for Improved Variety, Accuracy, and Coverage of AMR Alignments [9.74672460306765]
  We present algorithms for aligning components of Abstract Meaning Representation (AMR) spans in English sentences. We leverage unsupervised learning in combination with graphs, taking the best of both worlds from previous AMR. Our approach covers a wider variety of AMR substructures than previously considered, achieves higher coverage of nodes and edges, and does so with higher accuracy.
  arXiv  Detail & Related papers  (2021-06-10T18:46:32Z)
• Lightweight, Dynamic Graph Convolutional Networks for AMR-to-Text Generation [56.73834525802723]
  Lightweight Dynamic Graph Convolutional Networks (LDGCNs) are proposed. LDGCNs capture richer non-local interactions by synthesizing higher order information from the input graphs. We develop two novel parameter saving strategies based on the group graph convolutions and weight tied convolutions to reduce memory usage and model complexity.
  arXiv  Detail & Related papers  (2020-10-09T06:03:46Z)
• Improving AMR Parsing with Sequence-to-Sequence Pre-training [39.33133978535497]
  In this paper, we focus on sequence-to-sequence (seq2seq) AMR parsing. We propose a seq2seq pre-training approach to build pre-trained models in both single and joint way. Experiments show that both the single and joint pre-trained models significantly improve the performance.
  arXiv  Detail & Related papers  (2020-10-05T04:32:47Z)

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.