Sitemap
DAIR.AI

Democratizing Artificial Intelligence Research, Education, Technologies

Follow publication

When are Contextual Embeddings Worth Using?

Viktor
4 min readAug 1, 2020

--

Study

Training data volume

ML practitioners may find that for certain real-world tasks the large gains in efficiency [when using non-contextual embeddings] are well worth the cost of labelling more data. — Arora et al

Linguistic characteristics of the dataset

Animation the metric calculation and how it was used to evaluate the performance of the two kinds of embedding models.

Conclusion

--

--

DAIR.AI
DAIR.AI

Published in DAIR.AI

Democratizing Artificial Intelligence Research, Education, Technologies

Viktor
Viktor

Written by Viktor

Learning to write and writing to learn. Staying on top of current NLP research through sharing what I find interesting 🤖

No responses yet