This paper is based on the work carried out in the framework of the Verbmobil project, which is a limited-domain speech translation task (German-English). In the nal evaluation, the statistical approach was found to perform best among ve competing approaches. In this

Abstract. This article gives an overview of a new semantic-based transfer approach developed and applied within the Verbmobil Machine Translation project [22]. We present the declarative transfer formalism and discuss its implementation. The results presented in this paper have been integrated successfully in the Verbmobil system. 1

A large spoken dialogue translation system imposes both engineering and linguistic constraints on the way in which linguistic information is communicated between modules. We describe the design and use of interface terms, whose formal, functional and communicative role has been tested in a sequence of integrated systems and which have proven adequate to these constraints. 1

We describe a new' approach to syntactic generation with Head-Driven Phrase Structure Grammars (HPSG) that 'uses an extensive off-line. preprocessing step. Direct generation algo- rithms apply the phrase-structure rules (shemata) of the grammar on-line which is an com- Putationally expensive step. Instead, we collect off-line for every lexical type of the HPSG grammar all minimally complete projections .(called elementary trees) that can be derived with the schemata. This process is known as 'compiling HPSG to TAG' and derives a Lexicalized Tree-Adjoining Grammar (LTAG). The representation as an LTAG is 'fully lexicalized' in the sense that all grammatical information is directly encoded with the lexical item (as a 'set of elementary trees) and the combination operations are reduced from schema applications to the TAG primitives of adjunction and substitution. Given this LTAG, the generation task has a very different search .space that can be traversed very efficiently, avoiding the costly on-line applications of HPSG unification. The entire generation task from a semantic representation to a surface string is split into two tasks, a microplanner and a syntactic realizer. This paper discusses the syntactic generator and the preprocessing steps as implemented in the Verbmobil system.

This paper is a survey of the current machine translation research in the US, Europe and Japan. A short history of machine translation is presented first, followed by an overview of the current research work. Representative examples of a wide range of different approaches adopted by machine translation researchers are presented. These are described in detail along with a discussion of the practicalities of scaling up these approaches for operational environments. In support of this discussion, issues in, and techniques for, evaluating machine translation systems are addressed.

In this paper we present an ambiguity preserv-ing translation approach which transfers am-biguous LFG f-structure representations. It is based on packed f-structure representations which are the result of potentially ambiguous utterances. If the ambiguities between source and target language can be preserved, no un-packing during transfer is necessary and the generator may produce utterances which max-imally cover the underlying ambiguities. We convert the packed f-structure descriptions into a flat set of prolog terms which consist of pred-icates, their predicate argument structure and additional attribute-value information. Ambi-guity is expressed via local disjunctions. The flat representations facilitate the application of a Shake-and-Bake like transfer approach extended to deal with packed ambiguities. 1

We describe the design and function of a robust pro-cessing component which is being developed for the Verbmobil speech translation system. Its task con-sists of collecting partial analyses of an input utter-ance produced by three parsers and attempting to combine them into more meaningful, larger units. It is used as a fallback mechanism in cases where no complete analysis spanning the whole input can be achieved, owing to spontaneous speech phenomena or speech recognition errors.

Systems for spoken-language understanding can use prosodic information on the speech recognition side as well as the linguistic processing side. In the former case, prosody improves recognition accuracy and speed. In the latter case, it contributes to the computation of meaning. The following paragraphs discuss this meaning-related use of prosody in the spoken-language machine translation system Verbmobil (VM). The overall goal of the Verbmobil system is to provide speech-to-speech translations from both German and Japanese to English. The scenario is that of appointment scheduling dialogues between businessmen, and the overall system comprises some 50 modules which use a specifically designed architecture and protocol to communicate with each other [1].

from Japanese into a European language such as German or English is to determine definiteness of noun phrases in order to choose the correct determiner in the target language. Even though in Japanese, noun phrase reference is said to depend in large parts on the discourse context, we show that in many cases there also exist linguistic markers for definiteness. We use these to build a rule hierarchy that predicts 79,5% of the articles with an accuracy of 98,9% from syntactic-semantic properties alone, yielding an efficient pre-processing tool for the computationally expensive context checking.

This paper presents ongoing work on the development of the semantic transfer component of the multi-lingual speech-to-speech MT system Verbmobil. It focuses on the use of symbolic and statistical methods for the acquisition of semantic transfer rules, the disambiguation of translational ambiguities and the selection of appropriate rule candidates at runtime. 1 Introduction In this paper we describe how a combination of different methods and resources is used for the development of the transfer component of Verbmobil (Dorna & Emele 96b). Verbmobil (Wahlster 93) is a multi-lingual speech-to-speech MT system that is applied to the task of translating spoken language in the domain of appointment scheduling and travel planning. Currently, the system includes modules for German, English and Japanese. Over the last decades, neither pure stochastic approaches to machine translation (MT), such as the statistical approach (Brown et al. 90) or example-based MT (Sato & Nagao 90; Sumita et al. ...