Character-Level Chinese Dependency Parsing via Modeling Latent Intra-Word Structure
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913380079501312 |
|---|---|
| author | Hou, Yang Li, Zhenghua |
| author_facet | Hou, Yang Li, Zhenghua |
| contents | Revealing the syntactic structure of sentences in Chinese poses significant challenges for word-level parsers due to the absence of clear word boundaries. To facilitate a transition from word-level to character-level Chinese dependency parsing, this paper proposes modeling latent internal structures within words. In this way, each word-level dependency tree is interpreted as a forest of character-level trees. A constrained Eisner algorithm is implemented to ensure the compatibility of character-level trees, guaranteeing a single root for intra-word structures and establishing inter-word dependencies between these roots. Experiments on Chinese treebanks demonstrate the superiority of our method over both the pipeline framework and previous joint models. A detailed analysis reveals that a coarse-to-fine parsing strategy empowers the model to predict more linguistically plausible intra-word structures. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_03772 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Character-Level Chinese Dependency Parsing via Modeling Latent Intra-Word Structure Hou, Yang Li, Zhenghua Computation and Language Revealing the syntactic structure of sentences in Chinese poses significant challenges for word-level parsers due to the absence of clear word boundaries. To facilitate a transition from word-level to character-level Chinese dependency parsing, this paper proposes modeling latent internal structures within words. In this way, each word-level dependency tree is interpreted as a forest of character-level trees. A constrained Eisner algorithm is implemented to ensure the compatibility of character-level trees, guaranteeing a single root for intra-word structures and establishing inter-word dependencies between these roots. Experiments on Chinese treebanks demonstrate the superiority of our method over both the pipeline framework and previous joint models. A detailed analysis reveals that a coarse-to-fine parsing strategy empowers the model to predict more linguistically plausible intra-word structures. |
| title | Character-Level Chinese Dependency Parsing via Modeling Latent Intra-Word Structure |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2406.03772 |