Abstract
"中文语音实体关系三元组抽取任务(Chinese Speech Entity-Relation Triple Extraction Task, CSRTE)是第二十四届中国计算语言学大会中的一项技术评测,旨在从中文语音数据中自动识别并提取实体及其相互关系,构建结构化的语音关系三元组(头实体、关系、尾实体)。本任务的目标是提升中文语音关系三元组抽取的准确性与效率,增强模型在不同语境和复杂语音场景下的鲁棒性,实现从语音输入到文本三元组输出的全流程自动化处理。通过本次评测,有助于推动中文语音信息抽取技术的发展,促进语音与自然语言处理技术的深度融合,为智能应用提供更加丰富且精准的基础数据支持。此次评测共有257支队伍报名参赛,其中59支队伍提交了A榜成绩。成绩排名前15的队伍晋级A榜,并且表现突出的前朷支队伍提交了技术报告。"
- Anthology ID:
- 2025.ccl-2.58
- Volume:
- Proceedings of the 24th China National Conference on Computational Linguistics (CCL 2025)
- Month:
- August
- Year:
- 2025
- Address:
- Jinan, China
- Editors:
- Hongfei Lin, Bin Li, Hongye Tan
- Venue:
- CCL
- SIG:
- Publisher:
- Chinese Information Processing Society of China
- Note:
- Pages:
- 475–480
- Language:
- URL:
- https://aclanthology.org/2025.ccl-2.58/
- DOI:
- Bibkey:
- Cite (ACL):
- Wenxuan Mu, Jinzhong Ning, Yilin Pan, Paerhati Tulajiang, Yuanyuan Sun, SongTao Li, Yanxu Ji, Weiming Yin, Yijia Zhang, and Hongfei Lin. 2025. CCL25-Eval任务12总结报告:面向中文语音的实体关系三元组抽取. In Proceedings of the 24th China National Conference on Computational Linguistics (CCL 2025), pages 475–480, Jinan, China. Chinese Information Processing Society of China.
- Cite (Informal):
- CCL25-Eval任务12总结报告:面向中文语音的实体关系三元组抽取 (Mu et al., CCL 2025)
- Copy Citation:
- PDF:
- https://aclanthology.org/2025.ccl-2.58.pdf