Conditions for automatic dialogue interpretingConsidering a highly conventionalized type of dialogue (appointment scheduling), we suggest that the translation equivalent should consist of two parts, namely the discourse referents directly related to the purpose of the dialogue and the central dialogue act established by each source-language turn (SL turn). In the case of appointment scheduling, central discourse referents are temporal objects denoting potential dates for the appointment and their relations. Dialogue acts will have to be specified or modified according to the properties of this kind of dialogue.Our hypothesis, claiming that automatic interpretation of conventionalized dialogues should be based on the central information and the central illocutionary act of an utterance, also meets another crucial problem of spoken language processing, incomplete information, which may arise from different sources:• The speech recognizer will not always be able to recognize the whole SL turn. • Characteristic phenomena of spoken language are incomplete sentences, repairs, hesitations and breaking offs. • The linguistic knowledge available to the system is limited, it only covers a certain fragment of spoken language. • The contextual knowledge available to the system is incomplete, because nonverbal and situational cues cannot be processed. Translation equivalenceIn the field of translation theory, the problem of defining translation equivalents has been thoroughly discussed. Still there are many different definitions of equivalence relations and there has been much criticism of the notion of equivalence Brought to you by | Stockholms Universitet Authenticated Download Date | 9/30/15 4:18 PM
This article,1discusses the problems of machine translation focusing on a special task, i.e. automatic dialogue interpreting. In the translation of spoken discourse, there is an increasing tendency to use pragmatic information which is commonly associated with speech or dialogue acts in order to handle the problems encountered in speech processing.After discussing some characteristics of spoken language as well as principal constraints operating on speech-to-speech translation, we will give a very brief overview of existing approaches, and then switch to the extended description of a sample solution within the VERBMOBIL-Project where transfer is assisted by a dialogue-act component. The last section describes how, with limited use of available information, transfer based on dialogue acts might result in new solutions for existing problems.
Research on politeness has been proliferating for nearly four decades now, drawing on crosslinguistic data from a wide range of spoken and written languages and focusing on pragmatic, syntactic and grammatical features. Speech acts such as apologies and requests have been investigated as well as grammatical, i.e. morphological, morphosyntactic, and lexical forms of honorific systems, expressions of politeness, respect and disrespect. However, while discussions and research centering on the notion of face have been exceptionally numerous, the grammatical category of respect has not yet received as much attention, since Haase (1994), with the exception of Simon (2003). The present collection on "Respect and the 3rd person: Cross-linguistic Perspectives on Respect and Politeness" originated in the discussions in our panel at the DGfS annual meeting in 2009 on "Forms of expressing politeness / respect in discourse: Talking about a third party in different languages and varieties". The articles comprising this volume strive to expand our insights into the complex intersection between grammatical respect (i.e. linguistic features in morphology and/or morphosyntax), lexical expressions and discourse phenomena of politeness cross-linguistically, with special regard to the treatment of third-person non-participants and bystanders. Our aim is to shed new light on respect and politeness phenomena as well as on the relation between respect as a systematic category on the one hand and politeness as an outcome of linguistic interaction on the other.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.