Titlebook: CCKS 2021 - Evaluation Track; 6th China Conference Bing Qin,Haofen Wang,Jiangtao Zhang Conference proceedings 2022 Springer Nature Singapor

Vsd168

強(qiáng)壯

使成波狀

Nachrichtenübertragung über Satellitenation (VTC) task. Meanwhile we propose a joint training framework for VCC task and VTC task based on adversarial perturbations strategy. In the final leaderboard, we achieved 3rd place in the competition. The source code has been at Github (.).

foliage

https://doi.org/10.1007/978-3-7091-9534-5method, which improves the event detection ability of the model. At the same time, we use voting for model ensemble, so as to effectively utilize the advantages of multiple models. Our model achieves F1 score of 69.86% on the test set of CCKS2021 general fine-grained event detection task and ranks the third place in the competition.

名義上

Zufall und lebendiges Geschehenbel entity typing. In our approach, a semi-supervised learning strategy is conducted to cope with the unlabeled data, and a multi-label loss is employed to recognize the multi-label entity. An F1-score of 0.85498 on the final testing data is achieved, which verifies the performance of our approach, and ranks the second place in the task.

implore

Method Description for CCKS 2021 Task 3: A Classification Approach of Scholar Structured Informatioplied in academic searching. In this paper, a structured information extraction and match approach for structured scholar portrait from HTML web pages based on classification models is demonstrated in detail.

NIP

A Joint Training Framework Based on Adversarial Perturbation for Video Semantic Tags Classificationation (VTC) task. Meanwhile we propose a joint training framework for VCC task and VTC task based on adversarial perturbations strategy. In the final leaderboard, we achieved 3rd place in the competition. The source code has been at Github (.).

metropolitan

Data Augmentation Based on Pre-trained Language Model for Event Detection,method, which improves the event detection ability of the model. At the same time, we use voting for model ensemble, so as to effectively utilize the advantages of multiple models. Our model achieves F1 score of 69.86% on the test set of CCKS2021 general fine-grained event detection task and ranks the third place in the competition.

尖牙

混沌

A Biaffine Attention-Based Approach for Event Factor Extraction,several strategies, ensemble multi models to retrieve the final predictions. Eventually our approach performs on the competition data set well with an F1-score of 0.8033 and takes the first place on the leaderboard.