This is the authors' abstract. We don't add key points for this paper.
The purpose of the research is to answer the question whether linguistic information is retained in vector representations of sentences. We introduce a method of analysing the content of sentence embeddings based on universal probing tasks, along with the classification datasets for two contrasting languages. We perform a series of probing and downstream experiments with different types of sentence embeddings, followed by a thorough analysis of the experimental results. Aside from dependency parser-based embeddings, linguistic information is retained best in the recently proposed LASER sentence embeddings.
Answers are grounded in this paper and cite their sources.
No takes yet. Share an insight, caveat, or question.
Krasnowska-Kieraś et al. (2019) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: