Deep Multi-Instance Transfer Learning
Dimitrios Kotzias, Misha Denil, Phil Blunsom et al. · arXiv (Cornell University) · 2014
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.
Cited by 15 works. doi:10.48550/arxiv.1411.3128 Open-access PDF
Authors
References
- Efficient Estimation of Word Representations in Vector Space
- Distributed Representations of Words and Phrases and their Compositionality
- Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank
- Natural Language Processing (almost) from Scratch
- 10.1162/153244303322533223
- Learning Word Vectors for Sentiment Analysis
- Distributed Representations of Sentences and Documents
- Solving the multiple instance problem with axis-parallel rectangles
- Learning distributed representations of concepts.
- Support Vector Machines for Multiple-Instance Learning