Enhancing AMR-to-Text Generation with Dual Graph Representations
| Autor: | Iryna Gurevych, Leonardo F. R. Ribeiro, Claire Gardent |
|---|---|
| Přispěvatelé: | Ubiquitous Knowledge Processing (UKP), Technische Universität Darmstadt - Technical University of Darmstadt (TU Darmstadt), Natural Language Processing : representations, inference and semantics (SYNALP), Department of Natural Language Processing & Knowledge Discovery (LORIA - NLPKD), Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS), Technische Universität Darmstadt (TU Darmstadt), Centre National de la Recherche Scientifique (CNRS)-Université de Lorraine (UL)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université de Lorraine (UL)-Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), Centre National de la Recherche Scientifique (CNRS)-Université de Lorraine (UL)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université de Lorraine (UL)-Institut National de Recherche en Informatique et en Automatique (Inria) |
| Jazyk: | angličtina |
| Rok vydání: | 2019 |
| Předmět: |
FOS: Computer and information sciences
Theoretical computer science Computer Science - Computation and Language Computer science Message passing 02 engineering and technology Data_CODINGANDINFORMATIONTHEORY Graph [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI] 03 medical and health sciences 0302 clinical medicine Dual graph 030221 ophthalmology & optometry 0202 electrical engineering electronic engineering information engineering Text generation Graph (abstract data type) 020201 artificial intelligence & image processing [INFO]Computer Science [cs] Computation and Language (cs.CL) |
| Zdroj: | Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing, Nov 2019, Hong Kong, China. pp.3181--3192, ⟨10.18653/v1/D19-1314⟩ EMNLP/IJCNLP (1) |
| DOI: | 10.18653/v1/D19-1314⟩ |
| Popis: | Generating text from graph-based data, such as Abstract Meaning Representation (AMR), is a challenging task due to the inherent difficulty in how to properly encode the structure of a graph with labeled edges. To address this difficulty, we propose a novel graph-to-sequence model that encodes different but complementary perspectives of the structural information contained in the AMR graph. The model learns parallel top-down and bottom-up representations of nodes capturing contrasting views of the graph. We also investigate the use of different node message passing strategies, employing different state-of-the-art graph encoders to compute node representations based on incoming and outgoing perspectives. In our experiments, we demonstrate that the dual graph representation leads to improvements in AMR-to-text generation, achieving state-of-the-art results on two AMR datasets. Accepted as a long conference paper to EMNLP 2019 |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|