Automatic Storage and Indexing of Plan Derivations based on Replay Failures
نویسندگان
چکیده
When a case-based planner is retrieving a previous case in preparation for solving a new similar problem, it is often not aware of all of the implicit features of the new problem situation which determine if a particular case may be successfully applied. This means that some cases may fail to improve the planner’s performance. By detecting and explaining these case failures as they occur, retrieval may be improved incrementally. In this paper we provide a definition of case failure for the case-based planner, dersnlp (derivation replay in snlp), which solves new problems by replaying its previous plan derivations. We provide explanationbased learning (EBL) techniques for detecting and constructing the reasons for the case failure. We also describe how the case library is organized so as to incorporate this failure information as it is produced. Finally we present an empirical study which demonstrates the effectiveness of this approach in improving the performance of dersnlp.
منابع مشابه
Merge Strategies for Multiple Case Plan Replay
Planning by analogical reasoning is a learning method that consists of the storage, retrieval, and replay of planning episodes. Planning performance improves with the accumulation and reuse of a library of planning cases.Retrieval is driven by domain-dependent similarity metrics based on planning goals and scenarios. In complex situations with multiple goals, retrieval may find multiple past pl...
متن کاملDouble Derivations, Higher Double Derivations and Automatic Continuity
Let be a Banach algebra. Let be linear mappings on . First we demonstrate a theorem concerning the continuity of double derivations; especially that all of -double derivations are continuous on semi-simple Banach algebras, in certain case. Afterwards we define a new vocabulary called “-higher double derivation” and present a relation between this subject and derivations and finally give some ...
متن کاملStoring and Indexing Plan Derivations through Explanation-based Analysis of Retrieval Failures
Case-Based Planning (CBP) provides a way of scaling up domain-independent planning to solve large problems in complex domains. It replaces the detailed and lengthy search for a solution with the retrieval and adaptation of previous planning experiences. In general, CBP has been demonstrated to improve performance over generative (from-scratch) planning. However, the performance improvements it ...
متن کاملمدل دو مرحله ای شکاف- گلچین برای نمایه سازی خودکار متون فارسی
Purpose: Each language has its own problems. This leads to consider appropriate models for automatic indexing of every language. These models should concern the exhaustificity and specificity of indexing. This paper aims at introduction and evaluation of a model which is suited for Persian automatic indexing. This model suggests to break the text into the particles of candidate terms and to c...
متن کامل