What you can cram into a single $&!#* vector: probing sentence embeddings for linguistic properties

Conneau, Alexis; Kruszewski, German; Lample, Guillaume; Barrault, Loïc; Baroni, Marco

doi:http://dx.doi.org/10.18653/v1/P18-1198

What you can cram into a single $&!#* vector: probing sentence embeddings for linguistic properties

License

Citation

Conneau A, Kruszewski G, Lample G, Berrault L, Baroni M. What you can cram into a single $&!#* vector: probing sentence embeddings for linguistic properties. In: Gurevych I, Miyao Y, editors. Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers); 2018 Jul 15-20; Melbourne, Autralia. Stroudsburg (PA): Association for Computational Linguistics; 2016. p. 2126-36. DOI: 10.18653/v1/P18-1198

Abstract

Although much effort has recently been devoted to training high-quality sentence embeddings, we still have a poor understanding of what they are capturing. “Downstream” tasks, often based on sentence classification, are commonly used to evaluate the quality of sentence representations. The complexity of the tasks makes it however difficult to infer what kind of information is present in the representations. We introduce here 10 probing tasks designed to capture simple linguistic features of sentences, and we use them to study embeddings generated by three different encoders trained in eight distinct ways, uncovering intriguing properties of both encoders and training methods.

Description

Comunicació presentada a: 56th Annual Meeting of the Association for Computational Linguistics celebrat del 15 al 20 de juliol de 2018 a Melbourne, Australia.