Composition of conditional random fields for transfer learning

Authors:
Charles Sutton;Andrew McCallum
Affiliations:
University of Massachusetts, Amherst, MA;University of Massachusetts, Amherst, MA
Venue:
HLT '05 Proceedings of the conference on Human Language Technology and Empirical Methods in Natural Language Processing
Year:
2005

Citing 16
Cited 13

A model for reasoning about persistence and causation

Computational Intelligence
Representations of quasi-Newton matrices and their use in limited memory methods

Mathematical Programming: Series A and B
Multitask Learning

Machine Learning - Special issue on inductive transfer
Learning Information Extraction Rules for Semi-Structured and Free Text

Machine Learning - Special issue on natural language learning
Relational learning of pattern-match rules for information extraction

AAAI '99/IAAI '99 Proceedings of the sixteenth national conference on Artificial intelligence and the eleventh Innovative applications of artificial intelligence conference innovative applications of artificial intelligence
Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data

ICML '01 Proceedings of the Eighteenth International Conference on Machine Learning
Machine learning for information extraction in informal domains

Machine learning for information extraction in informal domains
A novel use of statistical parsing to extract information from text

NAACL 2000 Proceedings of the 1st North American chapter of the Association for Computational Linguistics conference
Dynamic conditional random fields: factorized probabilistic models for labeling and segmenting sequence data

ICML '04 Proceedings of the twenty-first international conference on Machine learning
Shallow parsing with conditional random fields

NAACL '03 Proceedings of the 2003 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology - Volume 1
Introduction to the CoNLL-2003 shared task: language-independent named entity recognition

CONLL '03 Proceedings of the seventh conference on Natural language learning at HLT-NAACL 2003 - Volume 4
Bayesian information extraction network

IJCAI'03 Proceedings of the 18th international joint conference on Artificial intelligence
Adaptive information extraction from text by rule induction and generalisation

IJCAI'01 Proceedings of the 17th international joint conference on Artificial intelligence - Volume 2
Relational learning via propositional algorithms: an information extraction case study

IJCAI'01 Proceedings of the 17th international joint conference on Artificial intelligence - Volume 2
Stacked sequential learning

IJCAI'05 Proceedings of the 19th international joint conference on Artificial intelligence
Introduction to the CoNLL-2005 shared task: semantic role labeling

CONLL '05 Proceedings of the Ninth Conference on Computational Natural Language Learning

Finding advertising keywords on web pages

Proceedings of the 15th international conference on World Wide Web
Dynamic Conditional Random Fields: Factorized Probabilistic Models for Labeling and Segmenting Sequence Data

The Journal of Machine Learning Research
A unified architecture for natural language processing: deep neural networks with multitask learning

Proceedings of the 25th international conference on Machine learning
A Joint Segmenting and Labeling Approach for Chinese Lexical Analysis

ECML PKDD '08 Proceedings of the European conference on Machine Learning and Knowledge Discovery in Databases - Part II
Search advertising using web relevance feedback

Proceedings of the 17th ACM conference on Information and knowledge management
Intra-document structural frequency features for semi-supervised domain adaptation

Proceedings of the 17th ACM conference on Information and knowledge management
Revealing the structure of medical dictations with conditional random fields

EMNLP '08 Proceedings of the Conference on Empirical Methods in Natural Language Processing
Entity extraction is a boring solved problem: or is it?

NAACL-Short '07 Human Language Technologies 2007: The Conference of the North American Chapter of the Association for Computational Linguistics; Companion Volume, Short Papers
A dual-layer CRFs based joint decoding method for cascaded segmentation and labeling tasks

IJCAI'07 Proceedings of the 20th international joint conference on Artifical intelligence
Semi-joint labeling for chinese named entity recognition

AIRS'08 Proceedings of the 4th Asia information retrieval conference on Information retrieval technology
Boundary detection of multiple related temporal duration of schedules in email

Proceedings of the sixth international conference on Knowledge capture
Natural Language Processing (Almost) from Scratch

The Journal of Machine Learning Research
Transfer learning in heterogeneous collaborative filtering domains

Artificial Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

Many learning tasks have subtasks for which much training data exists. Therefore, we want to transfer learning from the old, general-purpose subtask to a more specific new task, for which there is often less data. While work in transfer learning often considers how the old task should affect learning on the new task, in this paper we show that it helps to take into account how the new task affects the old. Specifically, we perform joint decoding of separately-trained sequence models, preserving uncertainty between the tasks and allowing information from the new task to affect predictions on the old task. On two standard text data sets, we show that joint decoding outperforms cascaded decoding.