相似音节增强的越汉跨语言实体消歧方法(Similar syllable enhanced cross-lingual entity disambiguation for Vietnamese-Chinese)
Yujuan Li (李裕娟), Ran Song (宋燃), Cunli Mao (毛存礼), Yuxin Huang (黄于欣), Shengxiang Gao (高盛祥), Shan Lu (陆杉)
Abstract
“跨语言实体消歧是在源语言句子中找到目标语言相对应的实体,对跨语言自然语言处理任务有重要支撑。现有跨语言实体消歧方法在资源丰富的语言上能得到较好的效果,但在资源稀缺的语种上效果不佳,其中越南语-汉语就是一对典型的低资源语言;另一方面,汉语和越南语是非同源语言存在较大差异,跨语言表征困难;因此现有的方法很难适用于越南语-汉语的实体消歧。事实上,汉语和越南语具有相似的音节特点,能够增强越-汉跨语言的实体表示。为更好的融合音节特征,我们提出相似音节增强的越汉跨语言实体消歧方法,缓解了越南语-汉语数据稀缺和语言差异导致性能不佳。实验表明,所提出方法优于现有的实体消歧方法,在R@1指标下提升了5.63%。”- Anthology ID:
- 2023.ccl-1.19
- Volume:
- Proceedings of the 22nd Chinese National Conference on Computational Linguistics
- Month:
- August
- Year:
- 2023
- Address:
- Harbin, China
- Editors:
- Maosong Sun, Bing Qin, Xipeng Qiu, Jing Jiang, Xianpei Han
- Venue:
- CCL
- SIG:
- Publisher:
- Chinese Information Processing Society of China
- Note:
- Pages:
- 208–219
- Language:
- Chinese
- URL:
- https://aclanthology.org/2023.ccl-1.19
- DOI:
- Cite (ACL):
- Yujuan Li, Ran Song, Cunli Mao, Yuxin Huang, Shengxiang Gao, and Shan Lu. 2023. 相似音节增强的越汉跨语言实体消歧方法(Similar syllable enhanced cross-lingual entity disambiguation for Vietnamese-Chinese). In Proceedings of the 22nd Chinese National Conference on Computational Linguistics, pages 208–219, Harbin, China. Chinese Information Processing Society of China.
- Cite (Informal):
- 相似音节增强的越汉跨语言实体消歧方法(Similar syllable enhanced cross-lingual entity disambiguation for Vietnamese-Chinese) (Li et al., CCL 2023)
- PDF:
- https://preview.aclanthology.org/ingest-acl-2023-videos/2023.ccl-1.19.pdf