Brigitte Grote

Ma(r)king concessions in English and German

Natural language generation aims at automatically verbalizing a “deep” representation of content, so that coherent and cohesive text originates. To produce such cohesive discourse, it is important to signal many of the relations holding between text segments to the reader by means of cue words, which we call discourse markers. Current generation systems usually do this in a simplistic way, e.g., by using one marker per relation. In reality, however, language offers a wide range of markers from which informed choices should be made. This paper suggests a method for equipping generators with the knowledge to select the most appropriate discourse marker from a set of candidate expressions. We concentrate on one area of discourse relations, the CONCESSION family, and identify its underlying semantics and pragmatics. On the basis of extensive corpus studies, we propose a new classification of CONCESSION markers in English and German, and then suggest a generation model for producing bilingual text that can inc...

From Natural Language Documents to Sharable Product Knowledge: A Knowledge Engineering Approach

A great part of the product knowledge in manufacturing enterprises is only available in the form of natural language documents. The know-how recorded in these documents is an essential resource for successful competition in the market. From the viewpoint of knowledge management, however, documents have a severe limitation: They do not capture the wealth of knowledge contained in these documents, since the entire knowledge is not spelled out on the linguistic surface. In order to overcome this limitation, the notion of a document as a particular kind of realization of (or view on) the underlying knowledge is introduced. This chapter discusses the major steps in realizing this approach to documents: Knowledge acquisition, knowledge representation, and techniques to automatically generate multilingual documents from knowledge bases. Further; we describe how the required product knowledge can be represented in a sharable and reusable way.

From communicative context to speech: integrating dialogue processing, speech production and natural language generation

Abstract The current article discusses the problem of appropriate intonation selection in Person-Machine dialogues, such as those expected in intelligent information systems when, for example, information retrieval is required. An approach is proposed which integrates the previously mostly separate paradigms of automatic natural language generation and speech synthesis in a Person-Machine dialogue scenario. The article introduces the two independent basis components adopted in the approach — a dialogue model for information retrieval (COR) and a text generation system for German (KOMET-PENMAN) — and develops from these a communicative-context-to-speech system architecture. This system provides for the flexible and context-appropriate selection of intonation patterns. The paper argues that such an approach removes some of the well-known gaps in both text-to-speech and concept-to-speech systems.

Speech Production in Human-Machine Dialogue: A Natural Language Generation Perspective

This article discusses speech production in dialogue from the perspective of natural language generation, focusing on the selection of appropriate intonation. We argue that in order to assign appropriate intonation contours in speech producing systems, it is vital to acknowledge the diversity of functions that intonation fulfills and to account for communicative and immediate contexts as major factors constraining intonation selection. Bringing forward arguments from a functional-linguistically motivated natural language generation architecture, we present a model of context-to-speech as an alternative to the traditional text-to-speech and concept-to-speech approaches.

Filter and Broker: An Integrated Architecture for Information Mediation of Dynamic Sources

When making decisions, access to information and proactive provision of information have become a business imperative. It can be expected that a tremendous amount of information needs can be satisfied much better today by what is offered in information networks, be it the Internet or a corporate intranet for knowledge management purposes. Yet there is also a fair chance that someone issuing a search request (e.g., on the Web) will get drowned in a flood of useless information and thus may miss the only useful tidbit that comes along with it. Likewise, producers of information may not be able to identify suitable customers. Various approaches have been suggested to cope with these problems, for instance, databases containing meta-information or data-warehouse systems. The most promising approach is the use of electronic marketplaces, where consumers and producers of information virtually meet for interaction. A special blend of information traders strives to satisfy the needs of both. In this article we propose an architecture that implements a new consumer-producer interaction and discuss the major components in detail: (a) brokers, who play the role of intermediaries between producers and consumers, and (b) filters, which try to reduce the load of information on either of the participants.

Planning efficient mixed initiative dialogue

A common feature of a number of current spoken dialogue systems for information retrieval is that little emphasis is placed on the generation of system contributions to the dialogue. In these systems, utterances have mostly been produced from templates, see for instance (Whittaker and Attwater 1994; Blomberg et al. 1993; Oerder and Aust 1993; Meng et al. 1996). This is a valid approach in system initiative type systems and in systems where utterances stand in a one-to-one relation to communicative goals. In mixed initiative systems, however, user and system might both lead the dialogue by providing several pieces of information and pursuing several different goals within one utterance. Hence, in this kind of dialogue we cannot predict what information the user chooses to provide, and hence cannot predict the systems response. We argue that in any system of reasonable size, the number of templates would be too large to determine a priori. Instead, in order to achieve efficient and cooperative dialogue, system utterances must be generated using natural language generation (NLG) techniques.

Using Context to Guide Information Search for Preventive Quality Management

Preventive quality management (PQM) is a very information-intensive task. Information as diverse as customer requirements, material specifications, and production line characteristics of a product as well as complaints related to similar products have to be taken into consideration when, e.g., predicting and evaluating possible failure modes of a product. However, only a subset of this information is actually relevant in a given stage of the PQM process and for a given person. In this paper, we exploit the notion of context to restrict the number of information sources accessed, make information selection more goal-directed, and finally, to customize system-user interaction.