Tree-adjoining grammars (TAG) have been proposed as a formalism for generation based on the intuition that the extended domain of syntactic locality that TAGs provide should aid in localizing semantic dependencies as well, in turn serving as an aid to generation from semantic representations. We demonstrate that this intuition can be made concrete by using the formalism of synchronous tree-adjoining grammars. The use of synchronous TAGs for generation provides solutions to several problems with previous approaches to TAG generation. Furthermore, the semantic monotonicity requirement previously advocated for generation gram- mars as a computational aid is seen to be an inherent property of synchronous TAGs.

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...

I survey some recent applications-oriented NL generation systems, and claim that despite very different theoretical backgrounds, these systems have a remarkably similar architecture in terms of the modules they divide the generation process into, the computations these modules perform, and the way the modules interact with each other. I also compare this 'consensus architecture' among applied NLG systems with psycholinguistic knowledge about how humans speak, and argue that at least some aspects of the consensns architecture seem to be in agreement with what is known about human language production, despite the fact that psycholinguistic plausibility was not in general a goal of the developers of the surveyed systems.

We present an algorithm for simultaneously constructing both the syntax and semantics of a sentence using a Lexicalized Tree Adjoining Grammar (LTAG). This approach captures naturally and elegantly the interaction between pragmatic and syntactic constraints on descriptions in a sentence, and the inferential interactions between multiple descriptions in a sentence. At the same

Previous stochastic approaches to generation do not include a tree-based representation of syntax. While this may be adequate or even advantageous for some applications, other applications profit fi'om using as much syutactic knowledge as is available, leaving to a stochastic model only those issues that are not determined by the grammar. We present initial results showing that a tree~based model derived fi'om a tree-annotated corpus improves on a tree model derived from an unarmorated corpus, and that a tree-based stochastic model with a hand- crafted grammar outperforms both.

We focus on the production of efficient descriptions of objects, actions and events. We define a type of efficiency, textual economy, that exploits the hearer's recognition of inferential links to material elsewhere within a sentence. Textual economy leads to efficient descriptions because the material that supports such inferences has been included to satisfy independent communicative goals, and is therefore overloaded in the sense of Pollack [18]. We argue that achieving textual economy imposes strong requirements on the representation and reasoning used in generating sentences. The representation must support the generator's simultaneous consideration of syntax and semantics. Reasoningmust enable the generator to assess quickly and reliably at any stage how the hearer will interpret the current sentence, with its '-(inc6mplete)syntax and'semantics. We show that these representational and reasoning requirements are met in the SPUD system for sentence planning and realization.

Natural language generation (NLG) is first and foremost a reasoning task. In this reasoning, a system plans a communicative act that will signal key facts about the domain to the hearer. In generating action descriptions, this reasoning draws on characterizations both of the causal properties of the domain and the states of knowledge of the participants in the conversation. This dissertation shows how such characterizations can be specified declaratively and accessed efficiently in NLG. The heart of this dissertation is a study of logical statements about knowledge and action in modal logic. By investigating the proof-theory of modal logic from a logic programming point of view, I show how many kinds of modal statements can be seen as straightforward instructions for computationally manageable search, just as Prolog clauses can. These modal statements provide sufficient expressive resources for an NLG system to represent the effects of actions in the world or to model an addressee whose knowledge in some respects exceeds and in other respects falls short of its own. To illustrate the use of such statements, I describe how the SPUD sentence planner exploits a modal knowledge base to

The acceptance of natural language generation systems strongly depends on their capability to facilitate the exchange of information with human users. Current generation systems consider the influence of situational factors on the content and the form of the resulting utterances. However, the need to time their processing flexibly is usually neglected although temporal factors play a central part when directly addressing a human communication partner. A short response time of a system is crucial for its effective use. Furthermore, some applications --- e.g., the simultaneous description of ongoing events --- even necessitate the interleaving of input consumption and output production, i.e. the use of an incremental processing mode. We claim that incremental processing is a central design principle for developing flexible and efficient generators for speech output. We discuss the advantages of parallel processing for incremental generation and several aspects of control of the generator...

Abstract not found

The complex sentences of newswire reports contain floating content units that appear to be opportunistically placed where the form of the surrounding text allows. We present a corpus analysis that identified precise semantic and syntactic constraints on where and how such information is realized. The result is a set of revision tools that form the rule base for a report generation system, allowing incremental generation of complex sentences. Introduction Generating reports that summarize quantitative data raises several challenges for language generation systems. First, sentences in such reports are very complex (e.g., in newswire basketball game summaries the lead sentence ranges from 21 to 46 words in length). Second, while some content units consistently appear in fixed locations across reports (e.g., game results are always conveyed in the lead sentence), others float, appearing anywhere in a report and at different linguistic ranks within a given sentence. Floating content uni...