2024
pdf
bib
abs
基于上下文学习与思维链策略的中文空间语义理解
Shiquan Wang (王士权)
|
Weiwei Fu (付薇薇)
|
Ruiyu Fang (方瑞玉)
|
Mengxiang Li (李孟祥)
|
Zhongjiang He (何忠江)
|
Yongxiang Li (李永翔)
|
Shuangyong Song (宋双永)
Proceedings of the 23rd Chinese National Conference on Computational Linguistics (Volume 3: Evaluations)
“本技术报告详细介绍了我们团队参加第四届中文空间语义理解评测(SpaCE2024)的方法和成果。SpaCE2024旨在全面测试机器对中文空间语义的理解能力,包括空间信息实体识别、空间信息实体识别、空间信息异常识别、空间方位信息推理和空间异形同义识别五个不同的任务。我们团队采用精心设计的prompt并结合微调的方式激发大语言模型的空间语义理解能力,构建了一个高效的空间语义理解系统。在最终的评估中,我们在空间信息实体识别题目中准确率为0.8947,在空间信息实体识别题目中准确率为0.9364,在空间信息异常识别题目中准确率为0.8480,在空间方位信息推理题目中准确率为0.3471,在空间异形同义识别题目中准确率为0.5631,测试集综合准确率为0.6024,排名第一。”
pdf
bib
abs
基于大小模型结合与半监督自训练方法的古文事件抽取
Weiwei Fu (付薇薇)
|
Shiquan Wang (王士权)
|
Ruiyu Fang (方瑞玉)
|
Mengxiang Li (李孟祥)
|
Zhongjiang He (何忠江)
|
Yongxiang Li (李永翔)
|
Shuangyong Song (宋双永)
Proceedings of the 23rd Chinese National Conference on Computational Linguistics (Volume 3: Evaluations)
“本文描述了队伍“TeleAI”在CCL2024古文历史事件类型抽取评测任务(CHED2024)中提交的参赛系统。该任务旨在自动识别出古代文本中的事件触发词与事件类型,其中事件类型判别被分为粗粒度和细粒度的事件类型判别两部分。为了提高古文历史事件类型抽取的性能,我们结合了大模型和小模型,并采用了半监督自训练的方法。在最终的评估中,我们在触发词识别任务得分0.763,粗粒度事件类型判别任务得分0.842,细粒度事件类型判别任务得分0.779,综合得分0.791,在所有单项任务和综合评分上均排名第一。”
pdf
bib
abs
Sentence Segmentation and Punctuation for Ancient Books Based on Supervised In-context Training
Shiquan Wang
|
Weiwei Fu
|
Mengxiang Li
|
Zhongjiang He
|
Yongxiang Li
|
Ruiyu Fang
|
Li Guan
|
Shuangyong Song
Proceedings of the Third Workshop on Language Technologies for Historical and Ancient Languages (LT4HALA) @ LREC-COLING-2024
This paper describes the participation of team “TeleAI” in the third International Chinese Ancient Chinese Language Information Processing Evaluation (EvalHan24). The competition comprises a joint task of sentence segmentation and punctuation, categorized into open and closed tracks based on the models and data used. In the final evaluation, our system achieved significantly better results than the baseline. Specifically, in the closed-track sentence segmentation task, we obtained an F1 score of 0.8885, while in the sentence punctuation task, we achieved an F1 score of 0.7129.