Deep Multi-Instance Transfer Learning
This addresses a labeling efficiency problem for NLP researchers, but it is incremental as it builds on existing methods.
The paper tackles the problem of inferring individual sentence ratings from full-review ratings by combining transfer, deep, and multi-instance learning, reducing the need for fine-grained human labeling.
We present a new approach for transferring knowledge from groups to individuals that comprise them. We evaluate our method in text, by inferring the ratings of individual sentences using full-review ratings. This approach, which combines ideas from transfer learning, deep learning and multi-instance learning, reduces the need for laborious human labelling of fine-grained data when abundant labels are available at the group level.