This paper reviews our recent work on applying inductive logic programming to the construction of natural language processing systems. We have developed a system, CHILL, that learns a parser from a training corpus of parsed sentences by inducing heuristics that control an initial overly-general shift-reduce parser. CHILL learns syntactic parsers as well as ones that translate English database queries directly into executable logical form. The ATIS corpus of airline information queries was used to test the acquisition of syntactic parsers, and CHILL performed competitively with recent statistical methods. English queries to a small database on U.S. geography were used to test the acquisition of a complete natural language interface, and the parser that CHILL acquired was more accurate than an existing hand-coded system. The paper also includes a discussion of several issues this work has raised regarding the capabilities and testing of ILP systems as well as a summary of our current research directions.
ML ID: 68
Planning systems have become an important tool for automating a wide variety of tasks. Control knowledge guides a planner to find solutions quickly and is crucial for efficient planning in most domains. Machine learning techniques enable a planning system to automatically acquire domain-specific search-control knowledge for different applications. Past approaches to learning control information have usually employed explanation-based learning (EBL) to generate control rules. Unfortunately, EBL alone often produces overly complex rules that actually decrease rather than improve overall planning efficiency. This paper presents a novel learning approach for control knowledge acquisition that integrates explanation-based learning with techniques from inductive logic programming. In our learning system SCOPE, EBL is used to constrain an inductive search for control heuristics that help a planner choose between competing plan refinements. SCOPE is one of the few systems to address learning control information for newer, partial-order planners. Specifically, this proposal describes how SCOPE learns domain-specific control rules for the UCPOP planning algorithm. The resulting system is shown to produce significant speedup in two different planning domains, and to be more effective than a pure EBL approach.
Future research will be performed in three main areas. First, SCOPE's learning algorithm will be extended to include additional techniques such as constructive induction and rule utility analysis. Second, SCOPE will be more thoroughly tested; several real-world planning domains have been identified as possible testbeds, and more in-depth comparisons will be drawn between SCOPE and other competing approaches. Third, SCOPE will be implemented in a different planning system in order to test its portability to other planning algorithms. This work should demonstrate that machine-learning techniques can be a powerful tool in the quest for tractable real-world planning.
ML ID: 67
This paper presents recent work using the CHILL parser acquisition system to automate the construction of a natural-language interface for database queries. CHILL treats parser acquisition as the learning of search-control rules within a logic program representing a shift-reduce parser and uses techniques from Inductive Logic Programming to learn relational control knowledge. Starting with a general framework for constructing a suitable logical form, CHILL is able to train on a corpus comprising sentences paired with database queries and induce parsers that map subsequent sentences directly into executable queries. Experimental results with a complete database-query application for U.S. geography show that CHILL is able to learn parsers that outperform a pre-existing, hand-crafted counterpart. These results demonstrate the ability of a corpus-based system to produce more than purely syntactic representations. They also provide direct evidence of the utility of an empirical approach at the level of a complete natural language application.
ML ID: 66
Theory refinement systems developed in machine learning automatically modify a knowledge base to render it consistent with a set of classified training examples. We illustrate a novel application of these techniques to the problem of constructing a student model for an intelligent tutoring system (ITS). Our approach is implemented in an ITS authoring system called Assert which uses theory refinement to introduce errors into an initially correct knowledge base so that it models incorrect student behavior. The efficacy of the approach has been demonstrated by evaluating a tutor developed with Assert with 75 students tested on a classification task covering concepts from an introductory course on the C++ programming language. The system produced reasonably accurate models and students who received feedback based on these models performed significantly better on a post test than students who received simple reteaching.
ML ID: 65
Most model-based diagnosis systems, such as GDE and Sherlock, have concerned discrete, static systems such as logic circuits and use simple constraint propagation to detect inconsistencies. However, sophisticated systems such as QSIM and QPE have been developed for qualitative modeling and simulation of continuous dynamic systems. We present an integration of these two lines of research as implemented in a system called QDOCS for multiple-fault diagnosis of continuous dynamic systems using QSIM models. The main contributions of the algorithm include a method for propagating dependencies while solving a general constraint satisfaction problem and a method for verifying the consistency of a behavior with a model across time. Through systematic experiments on two realistic engineering systems, we demonstrate that QDOCS demonstrates the best balance of generality, accuracy, and efficiency among competing methods.
ML ID: 64
Most research in planning and learning has involved linear, state-based planners. This paper presents SCOPE, a system for learning search-control rules that improve the performance of a partial-order planner. SCOPE integrates explanation-based and inductive learning techniques to acquire control rules for a partial-order planner. Learned rules are in the form of selection heuristics that help the planner choose between competing plan refinements. Specifically, SCOPE learns domain-specific control rules for a version of the UCPOP planning algorithm. The resulting system is shown to produce significant speedup in two different planning domains.
ML ID: 63
This paper describes an experimental comparison of seven different learning algorithms on the problem of learning to disambiguate the meaning of a word from context. The algorithms tested include statistical, neural-network, decision-tree, rule-based, and case-based classification techniques. The specific problem tested involves disambiguating six senses of the word ``line'' using the words in the current and proceeding sentence as context. The statistical and neural-network methods perform the best on this particular problem and we discuss a potential reason for this observed difference. We also discuss the role of bias in machine learning and its importance in explaining performance differences observed on specific problems.
ML ID: 62
This research describes the system RAPTURE, which is designed to revise rule bases expressed in certainty-factor format. Recent studies have shown that learning is facilitated when biased with domain-specific expertise, and have also shown that many real-world domains require some form of probabilistic or uncertain reasoning in order to successfully represent target concepts. RAPTURE was designed to take advantage of both of these results.
Beginning with a set of certainty-factor rules, along with accurately-labelled training examples, RAPTURE makes use of both symbolic and connectionist learning techniques for revising the rules, in order that they correctly classify all of the training examples. A modified version of backpropagation is used to adjust the certainty factors of the rules, ID3's information-gain heuristic is used to add new rules, and the Upstart algorithm is used to create new hidden terms in the rule base.
Results on refining four real-world rule bases are presented that demonstrate the effectiveness of this combined approach. Two of these rule bases were designed to identify particular areas in strands of DNA, one is for identifying infectious diseases, and the fourth attempts to diagnose soybean diseases. The results of RAPTURE are compared with those of backpropagation, C4.5, KBANN, and other learning systems. RAPTURE generally produces sets of rules that are more accurate that these other systems, often creating smaller sets of rules and using less training time.
ML ID: 61
Most approaches to learning control information in planning systems use explanation-based learning to generate control rules. Unfortunately, EBL alone often produces overly complex rules that actually decrease planning efficiency. This paper presents a novel learning approach for control knowledge acquisition that integrates explanation-based learning with techniques from inductive logic programming. EBL is used to constrain an inductive search for selection heuristics that help a planner choose between competing plan refinements. SCOPE is one of the few systems to address learning control information in the newer partial-order planners. Specifically, SCOPE learns domain-specific control rules for a version of the UCPOP planning algorithm. The resulting system is shown to produce significant speedup in two different planning domains.
ML ID: 60
A critical component of model-based intelligent tutoring sytems is a mechanism for capturing the conceptual state of the student, which enables the system to tailor its feedback to suit individual strengths and weaknesses. To be useful such a modeling technique must be practical, in the sense that models are easy to construct, and effective, in the sense that using the model actually impacts student learning. This research presents a new student modeling technique which can automatically capture novel student errors using only correct domain knowledge, and can automatically compile trends across multiple student models. This approach has been implemented as a computer program, ASSERT, using a machine learning technique called theory refinement, which is a method for automatically revising a knowledge base to be consistent with a set of examples. Using a knowledge base that correctly defines a domain and examples of a student's behavior in that domain, ASSERT models student errors by collecting any refinements to the correct knowledege base which are necessary to account for the student's behavior. The efficacy of the approach has been demonstrated by evaluating ASSERT using 100 students tested on a classification task covering concepts from an introductory course on the C++ programming language. Students who received feedback based on the models automatically generated by ASSERT performed significantly better on a post test than students who received simple teaching.
ML ID: 59
The problem of learning Bayesian networks with hidden variables is known to be a hard problem. Even the simpler task of learning just the conditional probabilities on a Bayesian network with hidden variables is hard. In this paper, we present an approach that learns the conditional probabilities on a Bayesian network with hidden variables by transforming it into a multi-layer feedforward neural network (ANN). The conditional probabilities are mapped onto weights in the ANN, which are then learned using standard backpropagation techniques. To avoid the problem of exponentially large ANNs, we focus on Bayesian networks with noisy-or and noisy-and nodes. Experiments on real world classification problems demonstrate the effectiveness of our technique.
ML ID: 58
Building accurate and efficient natural language processing (NLP) systems is an important and difficult problem. There has been increasing interest in automating this process. The lexicon, or the mapping from words to meanings, is one component that is typically difficult to update and that changes from one domain to the next. Therefore, automating the acquisition of the lexicon is an important task in automating the acquisition of NLP systems. This proposal describes a system, WOLFIE (WOrd Learning From Interpreted Examples), that learns a lexicon from input consisting of sentences paired with representations of their meanings. Preliminary experimental results show that this system can learn correct and useful mappings. The correctness is evaluated by comparing a known lexicon to one learned from the training input. The usefulness is evaluated by examining the effect of using the lexicon learned by WOLFIE to assist a parser acquisition system, where previously this lexicon had to be hand-built. Future work in the form of extensions to the algorithm, further evaluation, and possible applications is discussed.
ML ID: 57
This paper defines a new machine learning problem to which standard machine learning algorithms cannot easily be applied. The problem occurs in the domain of lexical acquisition. The ambiguous and synonymous nature of words causes the difficulty of using standard induction techniques to learn a lexicon. Additionally, negative examples are typically unavailable or difficult to construct in this domain. One approach to solve the lexical acquisition problem is presented, along with preliminary experimental results on an artificial corpus. Future work includes extending the algorithm and performing tests on a more realistic corpus.
ML ID: 56
This paper demonstrates the capabilities of FOIDL, an inductive logic programming (ILP) system whose distinguishing characteristics are the ability to produce first-order decision lists, the use of an output completeness assumption to provide implicit negative examples, and the use of intensional background knowledge. The development of FOIDL was originally motivated by the problem of learning to generate the past tense of English verbs; however, this paper demonstrates its superior performance on two different sets of benchmark ILP problems. Tests on the finite element mesh design problem show that FOIDL's decision lists enable it to produce better results than all other ILP systems whose results on this problem have been reported. Tests with a selection of list-processing problems from Bratko's introductory Prolog text demonstrate t hat the combination of implicit negatives and intensionality allow FOIDL to learn correct programs from far fewer examples than FOIL.
ML ID: 55
This paper presents results from recent experiments with CHILL, a corpus-based parser acquisition system. CHILL treats language acquisition as the learning of search-control rules within a logic program. Unlike many current corpus-based approaches that use statistical learning algorithms, CHILL uses techniques from inductive logic programming (ILP) to learn relational representations. CHILL is a very flexible system and has been used to learn parsers that produce syntactic parse trees, case-role analyses, and executable database queries. The reported experiments compare CHILL's performance to that of a more naive application of ILP to parser acquisition. The results show that ILP techniques, as employed in CHILL, are a viable alternative to statistical methods and that the control-rule framework is fundamental to CHILL's success.
ML ID: 54
This paper presents results on using a new inductive logic programming method called FOIDL to learn the past tense of English verbs. The past tense task has been widely studied in the context of the symbolic/connectionist debate. Previous papers have presented results using various neural-network and decision-tree learning methods. We have developed a technique for learning a special type of Prolog program called a first-order decision list, defined as an ordered list of clauses each ending in a cut. FOIDL is based on FOIL (Quinlan, 1990) but employs intensional background knowledge and avoids the need for explicit negative examples. It is particularly useful for problems that involve rules with specific exceptions, such as the past-tense task. We present results showing that FOIDL learns a more accurate past-tense generator from significantly fewer examples than all other previous methods.
ML ID: 53
This paper presents results on applying a version of the DOLPHIN search-control learning system to speed up a partial-order planner. DOLPHIN integrates explanation-based and inductive learning techniques to acquire effective clause-selection rules for Prolog programs. A version of the UCPOP partial-order planning algorithm has been implemented as a Prolog program and DOLPHIN used to automatically learn domain-specific search control rules that help eliminate backtracking. The resulting system is shown to produce significant speedup in several planning domains.
ML ID: 52