Actively Learning Probabilistic Subsequential Transducers
In this paper we investigate learning of probabilistic subsequential transducers in an activelearning environment. In our learning algorithm the learner interacts with an oracle byasking probabilistic queries on the observed data. We prove our algorithm in an identifi-cation in the limit model. We also provide experimental evidence to showthe correctnessand to analyze the learnability of the proposed algorithm.
Actively Learning Probabilistic Subsequential Transducers
Proceedings of ICGI
| Authors: | Hasan Ibne Akram, Colin de la Higuera, and Claudia Eckert |
| Year/month: | 2012/ |
| Booktitle: | Proceedings of ICGI |
| Volume: | 21 |
| Series: | JMLR:Workshop and Conference Proceedings |
| Publisher: | MIT Press |
| Fulltext: | click here |
Abstract |
|
| In this paper we investigate learning of probabilistic subsequential transducers in an activelearning environment. In our learning algorithm the learner interacts with an oracle byasking probabilistic queries on the observed data. We prove our algorithm in an identifi-cation in the limit model. We also provide experimental evidence to showthe correctnessand to analyze the learnability of the proposed algorithm. | |
Bibtex:
@inproceedings { akram2012,author = { Hasan Ibne Akram and Colin de la Higuera and Claudia Eckert},
title = { Actively Learning Probabilistic Subsequential Transducers },
year = { 2012 },
booktitle = { Proceedings of ICGI },
volume = { 21 },
series = { JMLR:Workshop and Conference Proceedings },
publisher = { MIT Press },
url = { http://jmlr.csail.mit.edu/proceedings/papers/v21/akram12a/akram12a.pdf },
}