What you can cram into a single vector: Probing sentence embeddings for linguistic properties
Alexis Conneau, German Kruszewski, Guillaume Lample, Loïc Barrault, Marco Baroni
Code Available — Be the first to reproduce this paper.
ReproduceCode
- github.com/facebookresearch/SentEvalOfficialIn paperpytorch★ 0
- github.com/facebookresearch/InferSentpytorch★ 2,280
- github.com/greenparachute/probing-with-noisepytorch★ 2
- github.com/sid7954/NLP-Toolkitpytorch★ 0
- github.com/maexe/linspector-webnone★ 0
- github.com/UKPLab/linspector-webnone★ 0
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.