论文标题
uio-uva在Semeval-2020任务1：词汇语义变化检测的上下文嵌入
UiO-UvA at SemEval-2020 Task 1: Contextualised Embeddings for Lexical Semantic Change Detection
论文作者
论文摘要
我们将上下文化的单词嵌入应用于Semeval-2020共享任务1中的词汇语义变化检测1。本文重点介绍子任务2，按时间随时间的时间来对单词进行排名。我们分析了两个上下文架构（BERT和ELMO）的性能和三种变更检测算法。我们发现，最有效的算法依赖于平均令牌嵌入与令牌嵌入之间的成对距离之间的余弦相似性。它们的表现要大于强大的基线（在评估后阶段，我们对Semeval-2020任务1提交了最佳子任务2），但有趣的是，特定算法的选择取决于测试集中黄金得分的分布。
We apply contextualised word embeddings to lexical semantic change detection in the SemEval-2020 Shared Task 1. This paper focuses on Subtask 2, ranking words by the degree of their semantic drift over time. We analyse the performance of two contextualising architectures (BERT and ELMo) and three change detection algorithms. We find that the most effective algorithms rely on the cosine similarity between averaged token embeddings and the pairwise distances between token embeddings. They outperform strong baselines by a large margin (in the post-evaluation phase, we have the best Subtask 2 submission for SemEval-2020 Task 1), but interestingly, the choice of a particular algorithm depends on the distribution of gold scores in the test set.
