Interactive Annotation Learning with Indirect Feature Voting
By Shilpa Arora, Eric Nyberg. 2009
15 citations recorded by the source corpus.
We demonstrate that a supervised annotation learning approach using structured features derived from tokens and prior annotations performs better than a bag of words approach. We present a general graph representation for automatically deriving these features from labeled data. Automatic feature selection based on class association scores requires a large amount of labeled data and direct voting can be difficult and error-prone for structured features, even for language specialists. We show that highlighted rationales from the user can be used for indirect feature voting and same performance can be achieved with less labeled data. We present our results on two annotation learning tasks for opinion mining from product and movie reviews.
Subfields: Artificial Intelligence, Evaluation & Benchmarks
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Christopher R'e
- Braden Hancock
- Percy Liang
- Paroma Varma
- Carolyn Penstein Rosé
- Mohit Bansal
- Eric Nyberg
- Greg Durrett
In Evaluation & Benchmarks
- Elijah Mayfield
- Carolyn Penstein Rosé
- Braden Hancock
- Eric Nyberg
- Shilpa Arora
- Paroma Varma
- Percy Liang
- Christopher R'e
Citations in the corpus
- Training Classifiers with Natural Language Explanations (2018, background): “text (Zaidan and Eisner, 2008; Arora and Nyberg, 2009), or marking relevant regions in images (Ahn et al.”
- Sentiment Classification using Automatically Extracted Subgraph Features (2010, methodology): “Although, in this work we are classifying sentences and not phrases, similar clues may be used for sentiment classification in sentences as well In this work, we use an efficient frequent subgraph mining algorithm (gSpan) (Yan and Han, 2002) to extract frequent subgraphs from a linguistic annotation”