Abstract not found

Automatically summarizing vast amounts of on-line quantitative data with a short natural language paragraph has a wide range of real-world applications. However, this specific task raises a number of difficult issues that are quite distinct from the generic task of language generation: conciseness, complex sentences, floating concepts, historical background, paraphrasing power and implicit content. In this thesis, I address these specific issues by proposing a new generation model in which a first pass builds a draft containing only the essential new facts to report and a second pass incrementally revises this draft to opportunistically add as many background facts as can fit within the space limit. This model requires a new type of linguistic knowledge: revision operations, which specifyies the various ways a draft can...

Large-scale natural language generation requires the integration of vast amounts of knowledge: lexical, grammatical, and conceptual.

One of the main challenges in automatically generating textual weather forecasts is choosing appropriate English words to communicate numeric weather data. A corpus-based analysis of how humans write forecasts showed that there were major differences in how individual writers performed this task, that is, in how they translated data into words. These differences included both different preferences between potential near-synonyms that could be used to express information, and also differences in the meanings that individual writers associated with specific words. Because we thought these differences could confuse readers, we built our SumTime-Mousam weather-forecast generator to use consistent data-to-word rules, which avoided words which were only used by a few people, and words which were interpreted differently by different people. An evaluation by forecast users suggested that they preferred SumTime-Mousam’s texts to human-generated texts, in part because of better word choice; this may be the first time that an evaluation has shown that nlg texts are better than human-authored texts. Key words: natural language processing, natural language generation, language and the word, information presentation, weather forecasts, lexical choice, idiolect Preprint submitted to Elsevier Science 2 June 2005

Text generation is a field of artificial intelligence aiming at modelling the process of natural language production. Text generation is best characterized as the process of making choices between alternate linguistic realizations under the constraints specified in the input to a text generator. Depending on the practical application, the input can take different forms- streams of numbers in report generation, traces

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...

... that interpret large, reversible grammars. Only little attention has been paid so far to the many small and simple applications that require coverage of a small sublanguage at different degrees of sophistication. The system TG/2 described in this pa- per can be smoothly integrated with deep generation processes, it integrates canned text, templates, and context-free rules into a single formalism, it allows for both textual and tabular output, and it can be parameterized according to linguistic preferences. These features are based on suitably restricted production system techniques and on a generic backtracking regime.

In this paper, we discuss the different strategies used in COMET (COordinated Multimedia Explanation Testbed) for selecting words with which the user is familiar. When pictures cannot be used to disambiguate a word or phrase, COMET has four strategies for avoiding unknown words. We give examples for each of these strategies and show how they are implemented in COMET.

Current research in natural language generation is situated in a computational linguistics tradition that was founded several decades ago. We critically analyse some of the architectural assumptions underlying existing systems and point out some problems in the domains of text planning and lexicalization. Guided by the identification of major generation challenges viewed from the angles of knowledge-based systems and cognitive psychology, we sketch some new directions for future research.

this paper is that neither has been implemented." ([Vaughan and McDonald, 1986], page 95). Although Meteer [1990] gives a detail description of the relationship between text structure and revision it is unclear how the proposed model could contribute to the choice problem of paraphrases (see section 5.2). How- ever, from the approach described above and from the system described in [Meteer, 1990] we can draw the following conclusions. Only the generatoFs input is marked. If the generator encounters alternative realizations the revision component is asked to make the decision. However, to be able to do this it needs detailed knowledge about the grammar. Therefore grammatical knowledge has to be duplicated. The linguistic realization component used in [Meteer, 1990] is MUMBLE-86 [McDonald, 1986]. The text structural representation level must completely specify the infor- mation to be expressed by the utterance. The mapping has to ensure that all the necessary linguistic information is present. Mumblers procedural grammar is used only for generation purposes. Therefore it is without reach for the revision model to take into account relevant sources of ambiguities