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.
翻译:单词嵌入在很多任务中都提高了NLP的先进水平。 理解密度神经表示的内容对于计算语义界来说最为重要。 我们建议重点将这些不透明的文字矢量与词典中发现的人文可读定义联系起来。 这个问题自然分为两个子任务: 将定义转换成嵌入, 将嵌入转换成定义。 这项任务是在多语言环境中进行的, 使用经过相同训练的类似嵌入组进行 。