Improving the accuracy and efficiency of MAP inference for Markov Logic

Sebastian Riedel
Proceedings of the 24th Conference on Uncertainty in Artificial Intelligence, PMLR R6:468-475, 2008.

Abstract

In this work we present Cutting Plane Inference (CPI), a Maximum A Posteriori (MAP) inference method for Statistical Relational Learning. Framed in terms of Markov Logic and inspired by the Cutting Plane Method, it can be seen as a meta algorithm that instantiates small parts of a large and complex Markov Network and then solves these using a conventional MAP method. We evaluate CPI on two tasks, Semantic Role Labelling and Joint Entity Resolution, while plugging in two different MAP inference methods: the current method of choice for MAP inference in Markov Logic, MaxWalkSAT, and Integer Linear Programming. We observe that when used with CPI both methods are significantly faster than when used alone. In addition, CPI improves the accuracy of MaxWalkSAT and maintains the exactness of Integer Linear Programming.

Cite this Paper

BibTeX
@InProceedings{pmlr-vR6-riedel08a, title = {Improving the accuracy and efficiency of MAP inference for Markov Logic}, author = {Riedel, Sebastian}, booktitle = {Proceedings of the 24th Conference on Uncertainty in Artificial Intelligence}, pages = {468--475}, year = {2008}, editor = {McAllester, David A. and Myllymäki, Petri}, volume = {R6}, series = {Proceedings of Machine Learning Research}, month = {09--12 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/r6/main/assets/riedel08a/riedel08a.pdf}, url = {https://proceedings.mlr.press/r6/riedel08a.html}, abstract = {In this work we present Cutting Plane Inference (CPI), a Maximum A Posteriori (MAP) inference method for Statistical Relational Learning. Framed in terms of Markov Logic and inspired by the Cutting Plane Method, it can be seen as a meta algorithm that instantiates small parts of a large and complex Markov Network and then solves these using a conventional MAP method. We evaluate CPI on two tasks, Semantic Role Labelling and Joint Entity Resolution, while plugging in two different MAP inference methods: the current method of choice for MAP inference in Markov Logic, MaxWalkSAT, and Integer Linear Programming. We observe that when used with CPI both methods are significantly faster than when used alone. In addition, CPI improves the accuracy of MaxWalkSAT and maintains the exactness of Integer Linear Programming.}, note = {Reissued by PMLR on 09 October 2024.} }
Endnote
%0 Conference Paper %T Improving the accuracy and efficiency of MAP inference for Markov Logic %A Sebastian Riedel %B Proceedings of the 24th Conference on Uncertainty in Artificial Intelligence %C Proceedings of Machine Learning Research %D 2008 %E David A. McAllester %E Petri Myllymäki %F pmlr-vR6-riedel08a %I PMLR %P 468--475 %U https://proceedings.mlr.press/r6/riedel08a.html %V R6 %X In this work we present Cutting Plane Inference (CPI), a Maximum A Posteriori (MAP) inference method for Statistical Relational Learning. Framed in terms of Markov Logic and inspired by the Cutting Plane Method, it can be seen as a meta algorithm that instantiates small parts of a large and complex Markov Network and then solves these using a conventional MAP method. We evaluate CPI on two tasks, Semantic Role Labelling and Joint Entity Resolution, while plugging in two different MAP inference methods: the current method of choice for MAP inference in Markov Logic, MaxWalkSAT, and Integer Linear Programming. We observe that when used with CPI both methods are significantly faster than when used alone. In addition, CPI improves the accuracy of MaxWalkSAT and maintains the exactness of Integer Linear Programming. %Z Reissued by PMLR on 09 October 2024.
APA
Riedel, S.. (2008). Improving the accuracy and efficiency of MAP inference for Markov Logic. Proceedings of the 24th Conference on Uncertainty in Artificial Intelligence, in Proceedings of Machine Learning Research R6:468-475 Available from https://proceedings.mlr.press/r6/riedel08a.html. Reissued by PMLR on 09 October 2024.

Related Material