论文标题
在Semeval-2020的UPB任务6：定义提取的验证语言模型
UPB at SemEval-2020 Task 6: Pretrained Language Models for Definition Extraction
论文作者
论文摘要
这项工作在Semeval-2020的第六任任务中提出了我们的贡献：从教科书（Defteval）中的自由文本中提取定义。该竞赛由三个具有不同粒度级别的子任务组成：（1）将句子分类为定义性或非定义性，（2）定义句子的标记，以及（3）关系分类。我们使用各种预审前的语言模型（即Bert，Xlnet，Roberta，Scibert和Albert）来解决比赛的三个子任务中的每个子任务。具体而言，对于每个语言模型变体，我们通过冻结其权重和微调来实验。我们还探索了一个多任务架构，该体系结构经过训练，可以共同预测第二个子任务和第三个子任务的输出。我们在Defteval数据集上评估的最佳性能模型获得了第一个子任务的第32位，第二个子任务的第37位。该代码可用于进一步研究：https：//github.com/avramandrei/defteval。
This work presents our contribution in the context of the 6th task of SemEval-2020: Extracting Definitions from Free Text in Textbooks (DeftEval). This competition consists of three subtasks with different levels of granularity: (1) classification of sentences as definitional or non-definitional,(2) labeling of definitional sentences, and (3) relation classification. We use various pretrained language models (i.e., BERT, XLNet, RoBERTa, SciBERT, and ALBERT) to solve each of the three subtasks of the competition. Specifically, for each language model variant, we experiment by both freezing its weights and fine-tuning them. We also explore a multi-task architecture that was trained to jointly predict the outputs for the second and the third subtasks. Our best performing model evaluated on the DeftEval dataset obtains the 32nd place for the first subtask and the 37th place for the second subtask. The code is available for further research at: https://github.com/avramandrei/DeftEval.
