Mooney R.J. 1997. Inductive Logic Programming for Natural Language Processing. In Proceedings of the 6th International Inductive Logic Programming Workshop, Berlin, pp. 3-24.  Home/Search   Document Details and Download   Summary   Related Articles   Check

....of the learned concepts. The use of programs from the logic of rst order as underlying representation makes ILP systems more ecient and more useful than conventional empirical machine learning systems. ILP systems were used successfully for the solution of several problems of the real world ([10], 11] Most of the representations in rst order logic, which are used in ILP systems, are versions of the Horn clauses based on Prolog. The two most used operators (see Figure 2) with which consistent programs can be generated are specialization and generalization. Consistent is the fact that a ....

R. Mooney. Inductive logic programming for natural language processing. In S. Muggleton, editor, Proceedings of the 6th International Workshop on Inductive Logic Programming, volume 1314 of Lecture Notes in Arti cial Intelligence, pages 3-24. Springer-Verlag, 1996.

....problem is intractable. While there are several successful heuristics for learning ILP programs, there are many practical difficulties with the inflexibility, brittleness and inefficient generic ILP systems. In most cases, researchers had to develop their own, problem specific, ILP systems [Mooney, 1997] but have not always escaped problems such as search control and inefficiency especially in large scale domains like NLP. This paper develops a different paradigm for relational learning that allows the use of general purpose and efficient propositional algorithms, but nevertheless learns ....

....this way it provides a natural and general way of using relational representations within a probabilistic framework. On the other hand, it turns out that generic ILP methods suffer brittleness and inefficiency and in many cases, researchers had to develop their own, problem specific, ILP systems [Mooney, 1997] . In particular, while time complexity is a significant problem for ILP methods, propositional learning is typically a lot more efficient. In our paradigm, due to the fact that our RGFs will generate a very large number of relational features (see search above) we adopt a specific learning ....

[Article contains additional citation context not shown here]

Raymond J. Mooney. Inductive logic programming for natural language processing. In (ILP-96), volume 1314 of LNAI, pages 3--24. Springer, 1997.

....trying to apply ILP techniques to the construction of natural language processing (NLP) systems. Mooney and Califf [11] have applied ILP techniques to learning the past tense of English verbs, and showed that ILP techniques are more effective than neuralnetwork and decision tree methods. Mooney [12] has also worked a system which learns a parser from a training corpus of parsed sentences. In [14] Muggleton presents how to use ILP techniques in NLP systems. We also believe that ILP techniques will find good application domains in the construction of NLP systems. In this paper, we present how ....

Mooney, R. J., Inductive Logic Programming for Natural Language Processing, in: Proceedings of the 6th International Workshop on Inductive Logic Programming, S. Muggleton (ed.), Springer-Verlag, Berlin, 1997, pp:3-21.

....(ILP) This is a discipline devoted to the inductive learning of Prolog programs from examples. The most relevant work in relation to natural language learning has been carried out by Mooney and colleagues at the University of Texas. A general survey of applications of ILP to NLP can be found in [151]. Particular works include applications to grammatical inference [247, 248] automatic induction of natural language interfaces for querying data bases [249, 222] information extraction tasks [216, 217, 29, 79, 80, 81, 30, 215] acquisition of verbal properties [153] text categorization [49, 50, ....

R. J. Mooney. Inductive Logic Programming for Natural Language Processing. S. Muggleton (Ed.), Inductive Logic Programming: Selected Papers from the 6th International Workshop. Springer Verlag, Berlin, 1997.

....king rook king illegal position ones [16] 4 YAYA and Natural Language Processing The main goal of YAYAisto be applied to NLP problems. Relational learning systems have been shown to be well suited for Natural Language Learning (NLL) ILP has been successfully applied in a number of NLP problems [15, 14, 6]. With this purpose, the widely used WordNet lexical ontology [13] has been integrated into YAYA. WordNet is automatically converted into a set of axioms that can be used: 1) To provide a background theory to the learning procedure; and (2) For reasoning purposes (once the learning procedure has ....

Raymond J. Mooney, `Inductive logic programming for natural language processing', in ########### ## ### ##### ######## ###### ######### ##### ########### ########, (1996).

....[HKMS98] parsing is conceived as a constraint satisfaction problem where constraints are meant to explicitly exclude some ungrammatical input whereas unexpected phenomena will be accepted by default if they do not violate explicit constraints. Furthermore constraints can be graded in order to smoothly model the notion of ungrammaticality (see also [Erb93] As in HPSG and LFG there is a coupling between syntactic and semantic level by means of mapping constraints which can be in turn graded. The syntactic and semantic layer may be implemented as autonomous computational entities which ....

....to rank, it is easy to see that a very large amount of corpora is required to assign reliable probabilities to familiar but with low frequent constructs. Many word combinations cannot be observed in the training material and thus cannot be estimated properly. Additional computations like smoothing [CG96] or backing off [Kat87] have to be used to alleviate this. 3. Lexicalization is not compatible with the current assignment of probabilities since they can be associated only with respect to the syntactic component of lexical entries. The criteria should be extended in order to ....

[Article contains additional citation context not shown here]

Raymond J. Mooney. Inductive Logic Programming for Natural Language Processing. http://www.cs.utexas.edu/users/ml. chillInduct.ps.gz.

....ILP has been used for learning grammar and semantics using the CHILL system [37] In this case, background knowledge and examples were taken from an existing database of US geographical facts. Each example consisted of a sentence paired with its semantics as shown in Figure 5 (figure taken from [17]) The data was gathered by asking subjects to generate appropriate questions. Each question was then paired with appropriate logical queries to give 250 examples. Figure 6 (taken from [17] shows CHILL s accuracy on progressively larger training sets averaged over 10 trials. The line labelled ....

....facts. Each example consisted of a sentence paired with its semantics as shown in Figure 5 (figure taken from [17] The data was gathered by asking subjects to generate appropriate questions. Each question was then paired with appropriate logical queries to give 250 examples. Figure 6 (taken from [17]) shows CHILL s accuracy on progressively larger training sets averaged over 10 trials. The line labelled Geobase shows the accuracy of an existing commercially developed hand coded system for the same domain. CHILL outperforms the existing system when trained on 175 or more examples. Examples ....

R.J. Mooney. Inductive logic programming for natural language processing. In S. Muggleton, editor, Proceedings of the Sixth International Workshop on Inductive Logic Programming, pages 3--21. Springer-Verlag, Berlin, 1997. LNAI 1314.

....outperforms Foidl and learns highly accurate morphological rules. 1 Introduction Machine learning methods been recently applied to a variety of tasks within the area of natural language processing [2] Inductive logic programming (ILP) systems have been applied to tasks such as learning to parse [6] and learning part of speech tagging [1] Learning of morphological structure has also been attempted with the ILP system Foidl [7] with the original experiment focused on relatively small samples of English. In subsequent work, Foidl was used to learn the synthesis and analysis rules for Slovene ....

R. J. Mooney. Inductive logic programming for natural language processing. In Proc. 6th Intl. Wshp. on Inductive Logic Programming, pages 3--22. Springer, Berlin, 1997.

....from most other forms of Machine Learning (ML) both by its use of an expressive representation language and its ability to make use of logically encoded background knowledge. This has allowed successful applications of ILP [1] in areas such as molecular biology [12, 10, 6, 5] and natural language [7, 3, 2] which both have rich sources of background knowledge and both benefit from the use of an expressive concept representation languages. For instance, the ILP system Progol has recently been used to generate comprehensible descriptions of the 23 most populated fold classes of proteins [14] where no ....

R.J. Mooney, `Inductive logic programming for natural language processing ', in Proceedings of the Sixth International Workshop on Inductive Logic Programming, ed., S. Muggleton, 3--21, Springer-Verlag, Berlin, (1997). LNAI 1314.

....1997; Jelinek, 1998) has been particularly influential in motivating the application of similar methods to other aspects of natural language processing. There is now a variety of work on applying learning methods to almost all other aspects of language processing as well (Charniak, 1993; Brill Mooney, 1997; Manning Schutze, 1999) including syntactic analysis (Charniak, 1997) semantic disambiguation and interpretation (Ng Zelle, 1997) discourse processing and information extraction (Cardie, 1997) and machine translation (Knight, 1997) Some concrete publication statistics clearly illustrate ....

....statistical methods for these tasks. In contrast, most of our own recent research on applying ILP to NLP has focused on learning to parse natural language database queries into a semantic logical form that produces an answer when executed in Prolog (Zelle Mooney, 1993, 1994, 1996; Zelle, 1995; Mooney, 1997; Thompson Mooney, 1999; Thompson, 1998; Thompson, Califf, Mooney, 1999) There is a long tradition of representing the meaning of natural language statements and queries in first order logic (Allen, 1995; Dowty, Wall, Peters, 1981; Woods, 1978) However, we know of no other recent research ....

Mooney, R. J. (1997). Inductive logic programming for natural language processing. In Muggleton, S. (Ed.), Inductive Logic Programming: Selected papers from the 6th International Workshop, pp. 3--22. Springer-Verlag, Berlin.

No context found.

Mooney R.J. 1997. Inductive Logic Programming for Natural Language Processing. In Proceedings of the 6th International Inductive Logic Programming Workshop, Berlin, pp. 3-24.

No context found.

Mooney R.J. (1997) Inductive Logic Programming for Natural Language Processing. In: Proceedings of the 6th International Inductive Logic Programming Workshop, Berlin, pp. 3-24.

No context found.

Mooney R. J. (1997) Inductive Logic Programming for Natural Language Processing. In Proceedings of the 6th Int. ILP Workshop, Berlin, pp. 3-24.

No context found.

Mooney, R. J. #1996#. Inductive logic programming for natural language processing. In: Proceedings of the 6th International Workshop on Inductive Logic Programming #S. Muggleton, Ed.#. Stockholm University, Royal Institute of Technology. pp. 205# 224.

No context found.

Mooney R.J. Inductive Logic Programming for Natural Language Processing. In Proceedings of the Sixth International Inductive Logic Programming Workshop, 1998.

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC