Roberto Garigliano

University of Durham: description of the LOLITA system as used in MUC-6

This document describes the LOLITA system and how it was extended to run the four MUC tasks, discusses the resulting systems performance on the required walk-through article, and then considers the performance of this system on the final evaluation set.

Evolutionary algorithms and a fractal inverse problem.

Over the past 30 years, algorithms that model natural evolution have generated robust search methods. These so-called evolutionary algorithms have been successfully applied to a wide range of problems. This paper discusses two types of evolutionary algorithms and their application to a problem in shape representation. Genetic algorithms and evolutionary programming, although both based on evolutionary principles, each place different emphasis on what drives the evolutionary process. While genetic algorithms rely on mimicking specific genotypic transformations, evolutionary programming emphasizes phenotypic adaptation. Results presented show the success of evolutionary programming in solving an example of a fractal inverse problem, but indicate that a genetic algorithm is not as successful. Reasons for this disparity are discussed.

The Durham Telephone Enquiry System

The Durham telephone enquiry system is a speaker/gender independent telephone enquiry service which operates in real-time. The system has been successfully applied to English and Italian telephone databases of up to 100,000 entries.The mechanism by which the telephone database is searched is a key feature of the enquiry system and is based upon a management-of-uncertainty methodology. The practical result of which is that there is no expectation that the users utterances will always be correctly interpreted by the speech recognition stage. This paper contains a description of the components of the system and how they are integrated. Issues which had to be addressed in ensuring that the system operates in real-time on ‘live’ input are also discussed.

Generation in the LOLITA system: an engineering approach

Natural Language Generation (NLG) is the automatic generation of Natural Language (NL) by computer in order to meet communicative goals. One aim of NL processing (NLP) is to allow more natural communication with a computer and, since communication is a two-way process, a NL system should be able to produce as well as interpret NL text. This research concerns the design and implementation of a NLG module for the LOLITA system. LOLITA (Large scale, Object-based, Linguistic Interactor, Translator and Analyser) is a general purpose base NLP system which performs core NLP tasks and upon which prototype NL applications have been built. As part of this encompassing project, this research shares some of its properties and methodological assumptions: the LOLITA generator has been built following Natural Language Engineering principles uses LOLITAs SemNet representation as input and is implemented in the functional programming language Haskell. As in other generation systems the adopted solution utilises a two component architecture. However, in order to avoid problems which occur at the interface between traditional planning and realisation modules (known as the generation gap) the distribution of tasks between the planner and plan-realiser is different: the plan-realiser, in the absence of detailed planning instructions, must perform some tasks (such as the selection and ordering of content) which are more traditionally performed by a planner. This work largely concerns the development of the plan- realiser and its interface with the planner. Another aspect of the solution is the use of Abstract Transformations which act on the SemNet input before realisation leading to an increased ability for creating paraphrases. The research has lead to a practical working solution which has greatly increased the power of the LOLITA system. The research also investigates how NLG systems can be evaluated and the advantages and disadvantages of using a functional language for the generation task.

An Intelligent Language Tutoring System for Handling Errors Caused by Transfer

This research addresses how an Intelligent Language Tutoring System can effectively help to solve a practical problem of transfer in students second language learning of Chinese. Our empirical data shows that the problem of transfer accounts for most of the errors observed in the linguistic output of English-speaking students in their study of Chinese. This accords with views of other experts on transfer in the field of second language learning, such as Selinker [15], Cornu [6], Sheen [16] and Cowan [7]. A technique of mixed grammar of Chinese and English is used to tackle the problem of transfer. In this paper, we describe the importance of transfer, explain the data that has been collected, present an overview of the three main models, demonstrate the technique that we use to handle errors of transfer and finally discuss how our system is going to be evaluated.

A Linguistic Approach to the Development of Object Oriented Systems using the NL System LOLITA

The problem tackled in this paper is that of using computer aided techniques to facilitate the building of Object Oriented models from natural language requirements. The authors believe that this could be achieved by the use of a Natural Language Processing System built according to the Natural Language Engineering principles such as LOLITA. The paper is devoted to explore this possibility and to show its potential using the Object Modeling Technique (OMT).

Reductions in the search space for deriving a fractal set of an arbitrary shape

At present, the problem of finding a quick and efficient way of representing an arbitrary shape as a set of contraction mappings (an iterated function system) is unresolved. Such a representation is particularly useful in shape representation since the primitives used to construct the shape will automatically have the correct morphology. Several attempts have been made to solve this problem and some of these are discussed. The main difficulty with these approaches is the large size and great complexity of the search space. This paper examines several constraints, all of a low computational complexity, which can be placed on each of the mappings which make up a possible solution. These constraints reduce the search space of four of the six coefficients of a mapping by between 20% and 85%, and of the other two by between 75% and 95% (the size of the reduction depends only on the size of the bounding box of the shape). Since these constraints apply to each mapping of an IFS, their cumulative effect on the search space is substantial. It is anticipated that these reductions in the search space can be used to aid a variety of search algorithms.

A model for learning by source control

The information we receive is often changing, inconsistent and incomplete, thus bound to generate contradictions. Clearly we must recover reasonably from inconsistencies if to make sense of the world. We introduce a model to cope with this situation. This paper continues the work presented in (6,7). We propose that an adaptive reasoning system should use a model of its sources, recognise patterns in their behaviour and adjust that model on the basis of evidence and general principles. The relation with TMS is then discussed.

Parallelising a Large Functional Program or: Keeping LOLITA Busy

In this paper we report on the ongoing parallelisation of LOLITA, a natural language engineering system. Although LOLITA currently exhibits only modest parallelism, we believe that it is the largest parallel functional program ever, comprising more than 47,000 lines of Haskell. LOLITA has the following interesting features common to real world applications of lazy languages: n n nthe code was not specifically designed for parallelism; n n nlaziness is essential for efficiency in LOLITA; n n nLOLITA interfaces to data structures outside the Haskell heap, using a foreign language interface; n n nLOLITA was not written by those most closely involved in the parallelisation.

Type Theoretic Semantics for SemNet

Semantic Networks have long been recognised as an important tool for modelling human type reasoning. This paper describes an attempt to give a formal semantics of a semantic network in constructive type theory.