From OpenCCG to AI Planning: Detecting Infeasible Edges in Sentence Generation
The search space in grammar-based natural language generation tasks can get very large, which is particularly problematic when generating long utterances or paragraphs. Using surface realization with OpenCCG as an example, we show that we can effectively detect partial solutions (edges) which cannot ultimately be part of a complete sentence because of their syntactic category. Formulating the completion of an edge into a sentence as finding a solution path in a large state-transition system, we demonstrate a connection to AI Planning which is concerned with this kind of problem. We design a compilation from OpenCCG into AI Planning allowing the detection of infeasible edges via AI Planning dead-end detection methods (proving the absence of a solution to the compilation). Our experiments show that this can filter out large fractions of infeasible edges in, and thus benefit the performance of, complex realization processes.
Code (0)
등록된 구현이 없습니다.
Tasks
SentenceText GenerationSimilar Papers 제목 키워드 기반
Density-based Feasibility Learning with Normalizing Flows for Introspective Robotic Assembly
Machine Learning (ML) models in Robotic Assembly Sequence Planning (RASP) need to be introspective on the predicted solutions, i.e. whether they are feasible or not, to circumvent potential efficiency degradation. Previo…
Out of Distribution (OOD) DetectionLSTM Hypertagging
Hypertagging, or supertagging for surface realization, is the process of assigning lexical categories to nodes in an input semantic graph. Previous work has shown that hypertagging significantly increases realization spe…
Text GenerationA Lexicon-Based Approach for Detecting Hedges in Informal Text
Hedging is a commonly used strategy in conversational management to show the speaker{'}s lack of commitment to what they communicate, which may signal problems between the speakers. Our project is interested in examining…
ManagementSentenceRejecting Hallucinated State Targets during Planning
Generative models can be used in planning to propose targets corresponding to states that agents deem either likely or advantageous to experience. However, imperfections, common in learned models, lead to infeasible hall…
Decision MakingOut-of-Distribution GeneralizationLLM-enhanced Scene Graph Learning for Household Rearrangement
The household rearrangement task involves spotting misplaced objects in a scene and accommodate them with proper places. It depends both on common-sense knowledge on the objective side and human user preference on the su…
Common Sense ReasoningGraph LearningTask Planning