Balancing expressiveness and simplicity in an interlingua for task based dialogue

Levin, Lori; Gates, Donna; Pianta, Dorcas; Cattoni, Roldano; Mana, Nadia; Peterson, Kay; Lavie, Alon; Pianesi, Fabio

doi:10.3115/1118656.1118664

Cited by 12 publications

(6 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The design principles of the NESPOLE! system are described in Levin et al (1998Levin et al ( , 2000Levin et al ( , 2002, Lavie et al (2001a), and Metze et al (2002).…”

Section: The Nespole! Multilingual Translation Systemmentioning

confidence: 96%

Generating Arabic text in multilingual speech-to-speech machine translation framework

Monem

Shaalan

Rafea

et al. 2008

Machine Translation

View full text Add to dashboard Cite

The interlingual approach to machine translation (MT) is used successfully in multilingual translation. It aims to achieve the translation task in two independent steps. First, meanings of the source-language sentences are represented in an intermediate language-independent (Interlingua) representation. Then, sentences of the target language are generated from those meaning representations. Arabic natural language processing in general is still underdeveloped and Arabic natural language generation (NLG) is even less developed. In particular, Arabic NLG from Interlinguas was only investigated using template-based approaches. Moreover, tools used for other languages are not easily adaptable to Arabic due to the language complexity at both the morphological and syntactic levels. In this paper, we describe a rule-based generation approach for task-oriented Interlingua-based spoken dialogue that transforms a relatively shallow semantic interlingual representation, called interchange format (IF), into Arabic text that corresponds to the intentions underlying the speaker's utterances. This approach addresses the handling of the problems of Arabic syntactic structure 123 206 A. Abdel Monem et al. determination, and Arabic morphological and syntactic generation within the Interlingual MT approach. The generation approach is developed primarily within the framework of the NESPOLE! (NEgotiating through SPOken Language in E-commerce) multilingual speech-to-speech MT project. The IF-to-Arabic generator is implemented in SICStus Prolog. We conducted evaluation experiments using the input and output from the English analyzer that was developed by the NESPOLE! team at Carnegie Mellon University. The results of these experiments were promising and confirmed the ability of the rule-based approach in generating Arabic translation from the Interlingua taken from the travel and tourism domain.

show abstract

“…The design principles of the NESPOLE! system are described in Levin et al (1998Levin et al ( , 2000Levin et al ( , 2002, Lavie et al (2001a), and Metze et al (2002).…”

Section: The Nespole! Multilingual Translation Systemmentioning

confidence: 96%

Generating Arabic text in multilingual speech-to-speech machine translation framework

Monem

Shaalan

Rafea

et al. 2008

Machine Translation

View full text Add to dashboard Cite

show abstract

“…Recently, several studies have addressed multilevel annotation of dialogues [1,12,15]; in our study, we focus on the two aspects of a DA indicated by [4]. One is the communicative function that corresponds to how the content should be used in order to update the context, and the other is a semantic content that corresponds to what the act is about.…”

Section: Annotation Of Communicative Function and Semantic Con-tent Imentioning

confidence: 99%

“…In this study, we adopt dialogue acts (DAs) [1,4,12,15,16] for this information and annotate DAs in the corpus.…”

Section: Poster Sessionmentioning

confidence: 99%

Dialogue act annotation for consulting dialogue corpus

Ohtake¹,

Misu²,

Hori³

et al. 2009

Proceedings of the 3rd International Universal Communication Symposium

View full text Add to dashboard Cite

This paper introduces a new corpus of consulting dialogues, which is designed for training a dialogue manager that can handle consulting dialogues through spontaneous interactions from the tagged dialogue corpus. We have collected 130 h of consulting dialogues in the tourist guidance domain. This paper outlines our taxonomy of dialogue act annotation that can describe two aspects of an utterances: the communicative function (speech act), and the semantic content of the utterance. We provide an overview of the Kyoto tour guide dialogue corpus and a preliminary analysis using the dialogue act tags.

show abstract

“…Recently, several studies have addressed multilevel annotation of dialogues (Levin et al, 2002;Bangalore et al, 2006;Rodriguez et al, 2007); in our study, we focus on the two aspects of a DA indicated by Bunt (2000). One is the communicative function that corresponds to how the content should be used in order to update the context, and the other is a semantic content that corresponds to what the act is about.…”

Section: Annotation Of Communicative Function and Semantic Content In Damentioning

confidence: 99%

“…In this study, we adopt dialogue acts (DAs) (Bunt, 2000;Shriberg et al, 2004;Bangalore et al, 2006;Rodriguez et al, 2007;Levin et al, 2002) for this information and annotate DAs in the corpus.…”

Section: Introductionmentioning

confidence: 99%