论文标题
Semeval-2022任务1：Codwoe-比较字典和单词嵌入
Semeval-2022 Task 1: CODWOE -- Comparing Dictionaries and Word Embeddings
论文作者
论文摘要
单词嵌入在许多任务中都在NLP中提高了最新技术。了解密集神经表示的内容是计算语义社区的最大兴趣。我们建议将这些不透明的单词向量与人类可读的定义联系起来，如词典所示。这个问题自然会分为两个子任务：将定义转换为嵌入，并将嵌入转换为定义。此任务是在多语言环境中使用的一组受过同质训练的嵌入式的集合。
Word embeddings have advanced the state of the art in NLP across numerous tasks. Understanding the contents of dense neural representations is of utmost interest to the computational semantics community. We propose to focus on relating these opaque word vectors with human-readable definitions, as found in dictionaries. This problem naturally divides into two subtasks: converting definitions into embeddings, and converting embeddings into definitions. This task was conducted in a multilingual setting, using comparable sets of embeddings trained homogeneously.
