paper-with-me

Papers

Language Generation via Combinatorial Constraint Satisfaction: A Tree Search Enhanced Monte-Carlo Approach

2020-11-24 · Findings of the Association for Computational Linguistics 2020 · Maosen Zhang, Nan Jiang, Lei LI, Yexiang Xue

Generating natural language under complex constraints is a principled formulation towards controllable text generation. We present a framework to allow specification of combinatorial constraints for sentence generation. We propose TSMH, an efficient method to generate high likelihood sentences with respect to a pre-trained language model while satisfying the constraints. Our approach is highly flexible, requires no task-specific training, and leverages efficient constraint satisfaction solving techniques. To better handle the combinatorial constraints, a tree search algorithm is embedded into the proposal process of the Markov chain Monte Carlo (MCMC) to explore candidates that satisfy more constraints. Compared to existing MCMC approaches, our sampling approach has a better mixing performance. Experiments show that TSMH achieves consistent and significant improvement on multiple language generation tasks.

📄 PDF Abstract BibTeX arXiv:2011.12334

Code (1)

Milozms/TSMH 공식 구현 pytorch

Tasks

Language ModelingLanguage ModellingSentenceText Generation

Similar Papers 제목 키워드 기반

MCTS Based Dispatch of Autonomous Vehicles under Operational Constraints for Continuous Transportation

2024-07-23 · Milan Tomy, Konstantin M. Seiler, Andrew J. Hill

Continuous transportation of material in the mining industry is achieved by the dispatch of autonomous haul-trucks with discrete haulage capacities. Recently, Monte Carlo Tree Search (MCTS) was successfully deployed in t…

Autonomous VehiclesScheduling

Graph Neural Networks for Maximum Constraint Satisfaction

2019-09-18 · Jan Toenshoff, Martin Ritzert, Hinrikus Wolf, Martin Grohe

Many combinatorial optimization problems can be phrased in the language of constraint satisfaction problems. We introduce a graph neural network architecture for solving such optimization problems. The architecture is ge…

Combinatorial OptimizationGraph Neural Network

Towards Geometry-Preserving Reductions Between Constraint Satisfaction Problems (and other problems in NP)

2024-10-31 · Gabriel Istrate

Motivated by phase transitions in combinatorial optimization problems, we define two kinds of geometry-preserving reductions between constraint satisfaction problems and other NP-search problems. We give a couple of exam…

Combinatorial Optimization

GenCO: Generating Diverse Designs with Combinatorial Constraints

2023-10-03 · Aaron Ferber, Arman Zharmagambetov, Taoan Huang, Bistra Dilkina 외

Deep generative models like GAN and VAE have shown impressive results in generating unconstrained objects like images. However, many design settings arising in industrial design, material science, computer graphics and m…

Combinatorial OptimizationImage Generation

An Effective Upperbound on Treewidth Using Partial Fill-in of Separators

2019-09-06 · Boi Faltings, Martin Charles Golumbic

Partitioning a graph using graph separators, and particularly clique separators, are well-known techniques to decompose a graph into smaller units which can be treated independently. It was previously known that the tree…