Reassessing Graph Linearization for Sequence-to-sequence AMR Parsing: On the Advantages and Limitations of Triple-Based Encoding
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912373559787520 |
|---|---|
| author | Kang, Jeongwoo Coavoux, Maximin Lopez, Cédric Schwab, Didier |
| author_facet | Kang, Jeongwoo Coavoux, Maximin Lopez, Cédric Schwab, Didier |
| contents | Sequence-to-sequence models are widely used to train Abstract Meaning Representation (Banarescu et al., 2013, AMR) parsers. To train such models, AMR graphs have to be linearized into a one-line text format. While Penman encoding is typically used for this purpose, we argue that it has limitations: (1) for deep graphs, some closely related nodes are located far apart in the linearized text (2) Penman's tree-based encoding necessitates inverse roles to handle node re-entrancy, doubling the number of relation types to predict. To address these issues, we propose a triple-based linearization method and compare its efficiency with Penman linearization. Although triples are well suited to represent a graph, our results suggest room for improvement in triple encoding to better compete with Penman's concise and explicit representation of a nested graph structure. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_08504 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Reassessing Graph Linearization for Sequence-to-sequence AMR Parsing: On the Advantages and Limitations of Triple-Based Encoding Kang, Jeongwoo Coavoux, Maximin Lopez, Cédric Schwab, Didier Computation and Language Sequence-to-sequence models are widely used to train Abstract Meaning Representation (Banarescu et al., 2013, AMR) parsers. To train such models, AMR graphs have to be linearized into a one-line text format. While Penman encoding is typically used for this purpose, we argue that it has limitations: (1) for deep graphs, some closely related nodes are located far apart in the linearized text (2) Penman's tree-based encoding necessitates inverse roles to handle node re-entrancy, doubling the number of relation types to predict. To address these issues, we propose a triple-based linearization method and compare its efficiency with Penman linearization. Although triples are well suited to represent a graph, our results suggest room for improvement in triple encoding to better compete with Penman's concise and explicit representation of a nested graph structure. |
| title | Reassessing Graph Linearization for Sequence-to-sequence AMR Parsing: On the Advantages and Limitations of Triple-Based Encoding |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2505.08504 |