Waking Up a Sleeping Rabbit: On Natural-Language Sentence Generation with FF

Koller, Alexander; Hoffmann, Jörg

doi:10.1609/icaps.v20i1.13429

Cited by 7 publications

(4 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another possible future direction is applying our approach to other domains, such as natural language generation. A connection between natural language generation and planning has been previously established (e.g., Koller and Hoffmann 2010). Grammars are explored widely for generating natural language and thus our approach should work almost out of the box, allowing for focused exploration of possible sentences.…”

Section: Discussion and Future Workmentioning

confidence: 99%

Exploring Context-Free Languages via Planning: The Case for Automating Machine Learning

Katz¹,

Ram²,

Sohrabi³

et al. 2020

ICAPS

View full text Add to dashboard Cite

While Machine Learning has achieved considerable success in recent years, this success crucially relies on human experts to select appropriate features, workflows, algorithms with their hyper-parameters, etc. Automating the role of the human expert has seen some attention from the Machine Learning community, with a dedicated workshop running since 2014 at one of the top Machine Learning conferences. % In this work, we propose to exploit multiple AI Planning tools for automating the human expert, generating Machine Learning pipelines automatically. We start from a knowledge about possible valid pipelines encoded as Context-Free Grammar, translate the problem of generating the corresponding language into Hierarchical Task Network (HTN) Planning model, further translate the HTN Planning model into a classical planning model. We use existing planners to produce multiple plans for the classical planning task, translate these plans into Machine Learning pipelines, train and evaluate these pipelines. Based on pipelines' accuracy feedback we update the classical planning model to improve the quality of pipelines obtained in next iterations. Using planning tools allows us to exploit the flexibility of model update instead of solution modification. We present an application that helps users to focus pipelines' exploration process by allowing to encode additional constraints on desired pipelines. Our experimental evaluation shows the feasibility of using planning techniques in this context.

show abstract

Section: Discussion and Future Workmentioning

confidence: 99%

Exploring Context-Free Languages via Planning: The Case for Automating Machine Learning

Katz¹,

Ram²,

Sohrabi³

et al. 2020

ICAPS

View full text Add to dashboard Cite

show abstract

“…Hence, planning techniques at the grounded level are limited to planning tasks where that blow-up is not prohibitive. It has been frequently observed that this excludes a variety of applications (e. g. [11,16,17,8,19]).…”

Section: Introductionmentioning

confidence: 99%

A Landmark-Cut Heuristic for Lifted Optimal Planning

Wichlacz,

Höller,

Fišer

et al. 2023

Frontiers in Artificial Intelligence and Applications

View full text Add to dashboard Cite

Lifted planning – finding plans directly on the PDDL input model – has attracted renewed attention during the last years. This avoids the process of grounding, which can become computationally prohibitive very easily. However, the main focus of recent research in this area has been on satisficing, i.e., (potentially) suboptimal planning. We present a novel heuristic for optimal lifted planning. Our basic idea is inspired by the LM-cut heuristic, which has been very successful in grounded optimal planning. Like LM-cut, we generate cut-based landmarks via back-chaining from the goal, generating cuts of partially grounded actions. However, exactly mimicking the ground formulation is not feasible, this includes computing the hmax heuristic several times for one computation of the LM-cut heuristic (which is already NP-hard to compute). We show that our heuristic is admissible and evaluate it in a cost optimal setting.

show abstract

“…A drawback of this approach is that the size of the grounded task representation may -in the worst casegrow exponentially with regard to action and predicate arity. But in many real world problems both can be quite large and the problems therefore quickly become infeasible to solve using grounded representations (see e. g. (Hoffmann et al 2006;Koller and Hoffmann 2010;Koller and Petrick 2011;Haslum 2011;Matloob and Soutchanski 2016)). Lifted planning does not rely on a grounded task representation and instead works directly on the lifted planning models.…”

Section: Introductionmentioning

confidence: 99%

Landmark Heuristics for Lifted Planning - Extended Abstract

Wichlacz

Höller

Hoffmann

2021

SOCS

View full text Add to dashboard Cite

Planning problems are usually modeled using lifted representations, they specify predicates and action schemas using variables over a finite universe of objects. However, current planning systems like Fast Downward need a grounded (propositional) input model. The process of grounding might result in an exponential blowup of the model size. This limits the application of grounded planning systems in practical applications. Recent work introduced an efficient planning system for lifted heuristic search, but the work on lifted heuristics is still limited. In this extended abstract, we introduce a novel lifted heuristic based on landmarks, which we extract from the lifted problem representation. Preliminary results on a benchmark set specialized to lifted planning show that there are domains where our approach finds enough landmarks to guide the search more effective than the heuristics available.

show abstract

Waking Up a Sleeping Rabbit: On Natural-Language Sentence Generation with FF

Cited by 7 publications

References 11 publications

Exploring Context-Free Languages via Planning: The Case for Automating Machine Learning

Exploring Context-Free Languages via Planning: The Case for Automating Machine Learning

A Landmark-Cut Heuristic for Lifted Optimal Planning

Landmark Heuristics for Lifted Planning - Extended Abstract

Contact Info

Product

Resources

About