Polyphone Disambiguation in Mandarin Chinese with Semi-Supervised Learning
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2021
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916357471207424 |
|---|---|
| author | Shi, Yi Wang, Congyi Chen, Yu Wang, Bin |
| author_facet | Shi, Yi Wang, Congyi Chen, Yu Wang, Bin |
| contents | The majority of Chinese characters are monophonic, while a special group of characters, called polyphonic characters, have multiple pronunciations. As a prerequisite of performing speech-related generative tasks, the correct pronunciation must be identified among several candidates. This process is called Polyphone Disambiguation. Although the problem has been well explored with both knowledge-based and learning-based approaches, it remains challenging due to the lack of publicly available labeled datasets and the irregular nature of polyphone in Mandarin Chinese. In this paper, we propose a novel semi-supervised learning (SSL) framework for Mandarin Chinese polyphone disambiguation that can potentially leverage unlimited unlabeled text data. We explore the effect of various proxy labeling strategies including entropy-thresholding and lexicon-based labeling. Qualitative and quantitative experiments demonstrate that our method achieves state-of-the-art performance. In addition, we publish a novel dataset specifically for the polyphone disambiguation task to promote further research. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2102_00621 |
| institution | arXiv |
| publishDate | 2021 |
| record_format | arxiv |
| spellingShingle | Polyphone Disambiguation in Mandarin Chinese with Semi-Supervised Learning Shi, Yi Wang, Congyi Chen, Yu Wang, Bin Computation and Language Artificial Intelligence The majority of Chinese characters are monophonic, while a special group of characters, called polyphonic characters, have multiple pronunciations. As a prerequisite of performing speech-related generative tasks, the correct pronunciation must be identified among several candidates. This process is called Polyphone Disambiguation. Although the problem has been well explored with both knowledge-based and learning-based approaches, it remains challenging due to the lack of publicly available labeled datasets and the irregular nature of polyphone in Mandarin Chinese. In this paper, we propose a novel semi-supervised learning (SSL) framework for Mandarin Chinese polyphone disambiguation that can potentially leverage unlimited unlabeled text data. We explore the effect of various proxy labeling strategies including entropy-thresholding and lexicon-based labeling. Qualitative and quantitative experiments demonstrate that our method achieves state-of-the-art performance. In addition, we publish a novel dataset specifically for the polyphone disambiguation task to promote further research. |
| title | Polyphone Disambiguation in Mandarin Chinese with Semi-Supervised Learning |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2102.00621 |