This thesis develops a new approach to automatic language generation that focuses on the need to produce a range of different paraphrases from the same input representation. One novelty of the system is its solidly grounding representations of word meaning in a background knowledge base, which enables the production of paraphrases stemming from certain inferences, rather than from purely lexical relationships alone. The system is designed in such a way that the paraphrasing mechanism extends naturally to a multilingual generator; specifically, we will be concerned with producing English and German sentences. The focus of the system is on lexical paraphrases, and one of the contributions of the thesis is in identifying, analyzing and extending relevant linguistic research so that it can be used to handle...

Verb alternations have been researched extensively in linguistics, but they have not yet received a systematic treatment in natural language generation systems; consequently, generators cannot make informed choices among alternatives. As a step towards overcoming this discrepancy, we review some linguistic work on several prominent alternations, revise and extend it, and suggest a set of rules that allow the series of alternated forms to be produced from a single base form of the verb, the lexical entry. The framework has been implemented in the Moose sentence generator, which can thus choose a particular verb alternation in order to accomplish generation goals such as placing emphasis on the most important element of the sentence.

This paper describes the input specification language of the WAG Sentence Generation system. The input is described in terms of Halliday's (1978) three meaning components, ideational meaning (the propositional content to be expressed), interactional meaning (what the speaker intends the listener to do in making the utterance), and textual meaning (how the content is structured as a message, in terms of theme, reference, etc.).

<F3.608e+05> This research aims to employ the user's domain knowledge by presenting a discourse strategy for introducing new concepts to the user: that of comparison with existing user knowledge. This strategy aims to increase the e#ciency of knowledge transfer from the system's domain model to the user, an important issue in Natural Language Generation<F2.341e+05><F3.608e+05> (nlg) and Intelligent Tutoring Systems<F2.341e+05><F3.608e+05> (its). The key contribution here is a computational model that identifies entities in the user's model of the domain that are su#ciently similar to the entity being introduced to draw comparisons.<F5.408e+05> Proposed Research<F7.1e+05> The Problem<F4.448e+05> In most<F2.341e+05> nlg<F4.448e+05> research to date, the model of the user's knowledge has been used to inhibit the production of text that repeats what the user already knows (see Paris 1987). This user model<F2.341e+05><F4.448e+05> (um) can be employed for more than this: in particular, it...

Abstract not found

ii Acknowledgements First and foremost, I want to thank my supervisor, Eric Yu, and my second reader, John Mylopoulos. They have suggested interesting directions, provided thoughtful feedback and timely responses, and always made time for discussions. In addition, I want to thank the IRG members who gave me a chance to present my evaluation ideas to them and suggested ways of improvement. This thesis would not have been possible without their guidance and support.

<F3.608e+05> This research aims to employ the user's domain knowledge by presenting a discourse strategy for introducing new concepts to the user: that of comparison with existing user knowledge. This strategy aims to increase the e#ciency of knowledge transfer from the system's domain model to the user, an important issue in Natural Language Generation<F2.341e+05><F3.608e+05> (nlg) and Intelligent Tutoring Systems<F2.341e+05><F3.608e+05> (its). The key contribution here is a computational model that identifies entities in the user's model of the domain that are su#ciently similar to the entity being introduced to draw comparisons.<F5.408e+05> Proposed Research<F7.1e+05> The Problem<F4.448e+05> In most<F2.341e+05> nlg<F4.448e+05> research to date, the model of the user's knowledge has been used to inhibit the production of text that repeats what the user already knows (see Paris 1987). This user model<F2.341e+05><F4.448e+05> (um) can be employed for more than this: in particular, it...

this paper: to apply various aspects of morphology to MT.

This paper describes the input specification language of the WAG Sentence Generation system. The input is described in terms of Halliday's (1978) three meaning components, ideational meaning (the propositional content to be expressed), interactional meaning (what the speaker intends the listener to do in making the utterance), and textual meaning (how the content is structured as a message, in terms of theme, reference, etc.). The input to

Information. Im Rahmen des Pipeline-Modells werden die dabei zu leistenden