Figure 1 - uploaded by Lori Levin
Content may be subject to copyright.
Source publication
The NESPOLE! System is a speech communication system designed to support multilingual interaction between common users and providers of e-commerce services over the Internet. The core of the system is a distributed interlingua-based speech-to-speech translation system, which is supported by multimodal capabilities that allow the two parties partici...
Context in source publication
Citations
... Khadivi and Ney integration the speech recognition and machine translation in computer-assisted translation [6]. Lavie et al., proposed a multilingual speech communication over the Internet [7]. These represent works show that machine translation, especially the multilingual machine translation plays an important role in IoT. ...
Machine translation, which will be used widely in human-computer interaction services to Internet of things (IoT), is a key technology in artificial intelligence field. This paper presents a minimum Bayes-risk (MBR) phrase table pruning method for pivot-based statistical machine translation (SMT). The SMT system requires a great amount of bilingual data to build a high-performance translation model. For some language pairs, such as Chinese-English, massive bilingual data are available on the web. However, for most language pairs, large-scale bilingual data are hard to obtain. Pivot-based SMT is proposed to solve the data scarcity problem: it introduces a pivot language to bridge the source language and the target language. Therefore, a source-target translation model based on well-trained source-pivot and pivot-target translation models can be derived with the pivot-based approach. However, due to the ambiguities of the pivot language, source and target phrases with different meanings may be wrongly matched. Consequently, the derived source-target phrase table may contain incorrect phrase pairs. To alleviate this problem, we apply the MBR method to prune the phrase table. The MBR pruning method removes the phrase pairs with the lowest risk from the phrase table. Experimental results on Europarl data show that the proposed method can both reduce the size of phrase tables and improve the performance of translations. This study also gives a useful reference to many IoT research field and smart web services.
... The field of MT witnessed the birth of new methods during the last decades, such as the well known statistical machine translation (Lopez 2008), the interlingua approach, and the Universal Network Language (UNL) system designed for Multilanguage translation. The quality of these last is "acceptable" but not "perfect", and remains a useful means of translation in such specialized domains as medicine (Grabar and Zweigenbaum, 2005;Baud et al., 2005) and for task-oriented domains such as speech translation for specific fields (Lavie, Pianesi, and Levin, 2006). MT computer systems function in two ways. ...
This paper tackles the problematic issue of the use of AT translation most particularly by Arabic-medium writers. Instead of relying of human experienced translaters, most Arabic-medium writers resort to AT and submit their translated texts without any proof-reading or editing. The data are taken from Adrar university's journal Al-Hakika.
... The usefulness of dialogue act recognition has thus been demonstrated in a number of large applicative systems, such as the VERBMOBIL [14], NE-SPOLE [15] and C-STAR [16] machine translation and dialogue systems that rely on dialogue act classification. ...
This work studies the usefulness of syntactic information in the context of automatic dialogue act recognition in Czech. Several pieces of evidence are presented in this work that support our claim that syntax might bring valuable information for dialogue act recognition. In particular, a parallel is drawn with the related domain of automatic punctuation generation and a set of syntactic features derived from a deep parse tree is further proposed and successfully used in a Czech dialogue act recognition system based on conditional random fields. We finally discuss the possible reasons why so few works have exploited this type of information before and propose future research directions to further progress in this area.
... The field of MT witnessed the birth of new methods during the last decades, such as the well known statistical machine translation (Lopez 2008), the interlingua approach, and the Universal Network Language (UNL) system designed for Multilanguage translation. The quality of these last is "acceptable" but not "perfect", and remains a useful means of translation in such specialized domains as medicine (Grabar and Zweigenbaum, 2005;Baud et al., 2005) and for task-oriented domains such as speech translation for specific fields (Lavie, Pianesi, and Levin, 2006). MT computer systems function in two ways. ...
in this communication, the concern was about the multiltude of mistakes found in abstracts of academic papers submitted for peer-reviewing , in particular those paper written in Arabic and which abstracts are in French or in English Most abstracts were automatic-text translations full of irregularities
... The challenge with the interlingua approach is to design a language independent intermediate representation that captures the semantic structures of all languages while being unambiguous. The interlingua has been used on limited task-oriented domains such as speech translation for specific domains [8]. Few efforts studied machine translation based on Interlingua, but on a limited scale, for Indian languages [20], Korean language [10] and Arabic language [19]. ...
This paper evaluates a machine translation (MT) system based on the interlingua approach, the Universal Network Language (UNL)
system, designed for Multilanguage translation. The study addresses evaluation of English-Arabic translation and aims at comparing
the MT systems based on UNL against other systems. Also, it serves to analyze the development of the system understudy by
comparing output at the sentence level. The evaluation is performed on the Encyclopedia of Life Support Systems (EOLSS), a
wide range corpus covering multiple linguistic and cultural backgrounds. Three automated metrics are evaluated, namely BLEU,
F1 and Fmean after being adapted to the Arabic language. Results revealed that the UNL MT outperforms other systems for all metrics.
... Évaluation subjective dans le cadre du projet NESPOLE! Le projet NESPOLE!(Lavie et al., 2006) met en situation de dialogue un agent touristique italophone, et un client américanophone, francophone ou germanophone. La traduction se fait via un pivot sémantique appelé IF construit pour la tâche 13 . ...
External methods for evaluating MT systems define various measures based on MT results and their usage. While operational systems are mostly evaluated since long by task-based methods, evaluation campaigns of the last years use (parsimoniously) quite expensive subjective methods based on unreliable human judgments, and (for the most part) methods based on reference translations, that are impossible to use during the real usage of a system, less correlated with human judgments when quality increases, and totally unrealistic in that they force to measure progress on fixed corpora, endlessly retranslated, and not on new texts to be translated for real needs. There are also numerous biases introduced by the desire to diminish costs, in particular the usage of parallel corpora in the direction opposed to that of their production, and of monolingual rather than bilingual judges. We prove the above by an analysis of the history of MT evaluation, of the « mainstream » evaluation methods, and of certain recent evaluation campaigns. We propose to abandon the reference-based methods in external evaluations, and to replace them by strictly task-based methods, while reserving them for internal evaluations.
... All classifiers were applied to the NESPOLE! corpus of interactions (Lavie et al., 2006), consisting of 8289 utterances in English (they also report scores for German data, that we do not reproduce here). The da set they use contained 70 labels, the most The SNNS neural network system was also used by Sanchis and Castro (2002). ...
... NEgotiating through SPOken Language in Ecommerce ) [12] was a EU funded project, running during years 2000-2002. It aimed at providing a system capable of supporting advanced needs in e-commerce and e-service by resorting to automatic speech-to-speech translation. ...
... Nespole! 2 (NEgotiating through SPOken Language in E- commerce) [12] was a EU funded project, running during years 2000-2002. It aimed at providing a system capable of supporting advanced needs in e-commerce and e-service by resorting to automatic speech-to-speech translation. ...
This paper focuses on the problem of language model adapta-tion in the context of Chinese-English cross-lingual dialogs, as set-up by the challenge task of the IWSLT 2009 Evalu-ation Campaign. Mixtures of n-gram language models are investigated, which are obtained by clustering bilingual train-ing data according to different available human annotations, respectively, at the dialog level, turn level, and dialog act level. For the latter case, clustering of IWSLT data was in fact induced through a comparable Italian-English parallel corpus provided with dialog act annotations. For the sake of adaptation, mixture weight estimation is performed either at the level of single source sentence or test set. Estimated weights are then transferred to the target language mixture model. Experimental results show that, by training different specific language models weighted according to the actual input instead of using a single target language model, signifi-cant gains in terms of perplexity and BLEU can be achieved.
In this paper, the authors demonstrate that language diversity imposes a significant barrier in message communication like Short Messaging Service (SMS). SMS and other messaging services, including Multimedia Messaging Service (MMS) and e-mail, are widely used for person-to-person and Business-to-Consumer (B2C) communications due to their reach, simplicity and reliability of delivery. Reach and service delivery can be further enhanced if the message is delivered in the recipient’s preferred language. Using language translation software and a database server, the authors show that the messages can be delivered as per language preference of the recipient irrespective of the language of the original message. They demonstrate the proposed mechanism can deliver a large number of services, such as education, health care management, notification in emergency situations, news and weather reports, to those who are currently not able to access them due to language barrier.
Along with the advancement of speech recognition technology and machine translation technology in addition to the fast distribution of mobile devices, speech-to-speech translation technology no longer remains as a subject of research as it has become popularized throughout many users. In order to develop a speech-to-speech translation system that can be widely used by many users, however, the system needs to reflect various characteristics of utterances by the users who are actually to use the speech-to-speech translation system other than improving the basic functions under the experimental environment. This study has established a massive language and speech database closest to the environment where speech-to- speech translation device actually is being used after mobilizing plenty of people based on the survey on users' demands. Through this study, it was made possible to secure excellent basic performance under the environment similar to speech-to-speech translation environment, rather than just under the experimental environment. Moreover, with the speech-to-speech translation UI, a user-friendly UI has been designed; and at the same time, errors were reduced during the process of translation as many measures to enhance user satisfaction were employed. After implementing the actual services, the massive database collected through the service was additionally applied to the system following a filtering process in order to procure the best-possible robustness toward both the details and the environment of the users' utterances. By applying these measures, this study is to unveil the procedures where multi-language speech-to-speech translation system has been successfully developed for mobile devices.
