nach oben

2018 | Buch

Kapitel lesen Erstes Kapitel lesen

Services Computing for Language Resources

herausgegeben von: Yohei Murakami, Donghui Lin, Toru Ishida

Verlag: Springer Singapore

Buchreihe : Cognitive Technologies

Enthalten in: Springer Professional "Wirtschaft+Technik" , Springer Professional "Technik" , Springer Professional "Wirtschaft"

Einloggen, um Zugang zu erhalten

Über dieses Buch

Describing the technologies to combine language resources flexibly as web services, this book provides valuable case studies for those who work in services computing, language resources, human–computer interaction (HCI), computer-supported cooperative work (CSCW), and service science. The authors have been operating the Language Grid, which wraps existing language resources as atomic language services and enables users to compose new services by combining them. From architecture level to service composition level, the book explains how to resolve infrastructural and operational difficulties in sharing and combining language resources, including interoperability of language service infrastructures, various types of language service policies, human services, and service failures.

The research based on the authors’ operating experiences of handling complicated issues such as intellectual property and interoperability of language resources contributes to exploitation of language resources as a service. On the other hand, both the analysis based on using services and the design of new services can bring significant results. A new style of multilingual communication supported by language services is worthy of analysis in HCI/CSCW, and the design process of language services is the focus of valuable case studies in service science. By using language resources in different ways based on the Language Grid, many activities are highly regarded by diverse communities.

This book consists of four parts: (1) two types of language service platforms to interconnect language services across service grids, (2) various language service composition technologies that improve the reusability, efficiency, and accuracy of composite services, (3) research work and activities in creating language resources and services, and (4) various applications and tools for understanding and designing language services that well support intercultural collaboration.

Inhaltsverzeichnis

Frontmatter

Language Service Platform

Frontmatter

Federated Grid Architecture for Language Services

Abstract

The existing platforms designed to ensure interoperability of language services define their own data format and annotation vocabularies. To construct a comprehensive language service infrastructure, various types of language services supporting different languages need to be connected to the platforms. However, it is difficult for a single operator to collect and organize services for two key reasons: what kinds of language services are registered depends on the purpose of the platforms, and the language resources are characterized by their locality. Therefore, federation of the platforms across regions is essential to establish the comprehensive infrastructure desired. In this chapter, we extend the existing service grid architecture to federate heterogeneous as well as homogeneous language service platforms. To this end, we introduce an upper-level ontology for a service grid that facilitates the semantic integration of domain ontologies and guides the development of new domain ontologies. Moreover, we also introduce a federated grid architecture that can share language service registries, and compose language services across service grids.

Yohei Murakami, Takao Nakaguchi, Donghui Lin, Toru Ishida

Language Mashup: Personalized Language Service Platform

Abstract

The aim of the Language Grid is to enable users to develop new language services by sharing and combining any existing language resources as language services. To implement this concept, we had to address the following problems: (1) only organization agents can register and invoke services, i.e., private users cannot invoke services on the Language Grid directly. Private users are able to use only the applications that have been developed and published non-commercially; (2) using the resources of mobile devices and services in the cloud is hindered by mismatches such as different communication protocols and different input and output methods. This chapter introduces a language service infrastructure for personal use called Language Mashup. It enables users to develop and install domain-specific multilingual applications on their smart personal devices by combining various kinds of language services created from the language resources provided by both academia and industry, and located on cloud servers or on mobile devices.

Masayuki Otani, Nguyen Cao Hong Ngoc, Takao Nakaguchi, Donghui Lin

Language Service Composition

Frontmatter

Language Service Composition Based on Higher Order Functions

Abstract

To support multi-language activities, various composite services are created by a service composition that combines existing services or changes the combination of services composed by existing composite services. Multi-language activities have a wide variety of domains and their needs may change with the participants or situations, so service composition must be able to freely create various services to suit the languages of the participants and/or domains of the activity targets. Since existing service composition technologies relies on the deployment process of created composite services toward service infrastructure for users to find and execute them, delay and costs are expensive. To solve this problem, we propose a method that introduces the concept of higher order functions. In concrete, we regard services as functions and pass the functions invoked from composite services as runtime parameters of composite services to compose services without any deployment processes, this yields service composition that can efficiently support multi-language activities. We apply the proposals to Language Grid, designed to gather and provide language services, and evaluate the results. They show that our proposals can create various composite services at runtime with quite practical overheads.

Takao Nakaguchi, Yohei Murakami, Donghui Lin, Toru Ishida

Policy-Aware Language Service Composition

Abstract

Many language resources are being shared as web services to process data on the Internet. As dataset size keeps growing, language services are experiencing more big data problems, such as the storage and processing overheads caused by the huge amounts of multilingual texts. Parallel execution and cloud technologies are the keys to making service invocation practical. In the Service-Oriented Architecture approach, service providers typically employ policies to limit parallel execution of the services based on arbitrary decisions. In order to attain optimal performance, users need to adapt to the services policies. A composite service is a combination of several atomic services provided by various providers. To use parallel execution for greater composite service efficiency, the degree of parallelism (DOP) of the composite services need to be optimized by considering the policies of all atomic services. We propose a model that embeds service policies into formulae and permits composite service performance to be calculated. From the calculation results, we can predict the optimal DOP for the composite service that allows the best performance to be attained. Extensive experiments are conducted on real-world translation services. The analysis results show that our proposed model has good prediction accuracy in identifying optimal DOPs for composite services.

Trang Mai Xuan, Yohei Murakami, Toru Ishida

Optimizing Crowdsourcing Workflow for Language Services

Abstract

Recently, attempts have been to request translation services from anonymous crowds. Compared with platform-based language services, services performed by humans have the advantages of flexibility and quality. However, due to the nature of human services the results are not consistent and quality is not assured. This research tries to solve this problem by creating workflows that make collaboration among crowdsourcing workers far more effective and efficient. We model workers and tasks, and calculate the optimal workflow. To confirm the feasibility of this model, we conduct a computational experiment to calculate the best workflow under various parameters. The results are consistent with existing research so the model is useful in understanding crowdsourcing workflows. In addition, a system is developed for realizing crowdsourcing workflows for translation services. Finally, we develop a translation interface that demonstrates the feasibility of the proposed method.

Shinsuke Goto, Toru Ishida, Donghui Lin

Cascading-Failure Tolerance for Language Service Networks

Abstract

One of the main features of The Language Grid is its support for service composition, i.e. creating new language services that meet user requirements by combining the existing ones. Despite the potential of service composition, such a service-oriented computing (SOC) application may experience cascading failure when a disruption on one or more component services is propagated to the composite services that combine them. As the number of language services grows, composite language services will become more common, and thus understanding cascading failure among language services becomes more important. This chapter investigates how failure may propagate among language services and how to improve language service tolerance to cascading failure. To this end, the dependency between language services is modeled as service network on which cascading failure is simulated and analyzed. We also generated service networks in scale-free, exponential, and random topology to analyze how cascading failure occurs in different topology. The simulation reveals that service networks with scale-free topology have better cascading-failure tolerance compares to that of other topology.

Kemas M. Lhaksmana, Toru Ishida, Yohei Murakami

Language Resources and Services Creation

Frontmatter

A Constraint Approach to Lexicon Induction for Low-Resource Languages

Abstract

Bilingual lexicon is a useful language resource, but such data rarely available for lower-density language pairs, especially for those that are closely related. The lack or absence of parallel and comparable corpora makes bilingual lexicon extraction becomes a difficult task. Using a third language to link two other languages is a well-known solution in low-resource situation, which usually requires only two input bilingual lexicons to automatically induce the new one. This approach, however, is weak in measuring semantic distance between bilingual word pairs because it has never been demonstrated to utilize the complete structures of the input bilingual lexicons as dropped meanings negatively influence the result. This research discuss a constraint approach to pivot-based lexicon induction in case the target language pair are closely related. We create constraints from language similarity and model the structures of the input dictionaries as an optimization problem whose solution produces optimally correct target bilingual lexicon. In addition, we enable created bilingual lexicons of low-resource languages accessible through service grid federation.

Mairidan Wushouer, Donghui Lin, Toru Ishida, Yohei Murakami

Language Service Design Based on User-Centered QoS

Abstract

To design complicated language services for intercultural collaboration, it is important to consider how to compose different atomic language services so as to satisfy the requirements raised by the users. In the research area of services computing, many approaches to QoS-aware service composition have been proposed, where the assumption is that the QoS of a composite service can be calculated by aggregating the individual QoS values of atomic services. However, the QoS of a composite service is difficult to predict due to the QoS uncertainty of services in the real world. In this chapter, we address the above concerns by proposing a service design approach based on user-centered QoS and then confirming it in a case study of language service design for multi-language communication. To achieve this goal, we first introduce a QoS model to address the issues of user requirements and QoS uncertainty. We then propose a service design process that consists of composite service generation, participatory simulation, QoS evaluation and QoS data update. Finally, we introduce a field study of multi-language service design for agricultural knowledge communication to elucidate the benefits of our proposal approach.

Donghui Lin, Toru Ishida, Yohei Murakami

Understanding and Designing Language Services

Frontmatter

Consistency Analysis in Multi-language Knowledge Sharing System

Abstract

Unprecedented growth in knowledge sharing among multi-language communities, both common and distinct languages, has raised the possibility of sharing inconsistent content. Though popular with traditional system, the approach to explicitly state consistency rules to avoid inconsistency is practically not suited for multi-language knowledge sharing system because of sheer complexity. Alternatively this chapter focuses on potential cause of inconsistency, cases such as content omitted, content updates not propagated and content conflicts. Ignoring such cases in knowledge sharing has undesirable consequences: community bias, global and local inconsistency and regional discrepancies. Consistency constraints from opposing knowledge sharing goals among communities is another issue. Due to which consistency policy ranges from rigid ‘one to one consistency’ to non-rigid ‘consistency where needed’. This chapter contributes with (a) process-based approach for multilingual content synchronization to leverage knowledge equally and (b) propagation-based approach to analyze community preferences when sharing specific content categories/geographic regions, to customize knowledge sharing; a value add-on to designing language services adhering to knowledge sharing goals.

Amit Pariyar, Yohei Murakami, Donghui Lin, Toru Ishida

Supporting Non-native Speakers’ Listening Comprehension with Automated Transcripts

Abstract

Various language services exist to support the listening comprehension of non-native speakers (NNSs). One important service is to provide NNSs with real-time transcripts generated by automatic speech recognition (ASR) technologies. The goal of our research is to explore the effects of ASR transcripts on the listening comprehension of NNSs and consider how to support NNSs with ASR transcripts more effectively. To reach our goal, we ran three studies. The first study investigates the comprehension problems faced by NNSs, and the second study examines how ASR transcripts impact their listening comprehension, e.g., what types of comprehension problems could and could not be solved by reading ASR transcripts. Finally, the third study explores the potential of using eye-tracking data to detect their comprehension problems. Our data analysis identified thirteen types of listening comprehension problems. ASR transcripts helped the NNSs solve certain problems, e.g., “failed to recognize words they know.” However, the transcripts did not solve problems such as “lack of vocabulary,” and indeed NNS burden was increased. Results also show that from eye-tracking data we can make reasonably accurate predictions (83.8%) about the types of problems encountered by NNSs. Our findings provide insight into ways of designing real-time adaptive support systems for NNSs.

Xun Cao, Naomi Yamashita, Toru Ishida

Translation Agent

Abstract

When applying Language Grid for multilingual communication support, it is important to understand the effects of the machine translation service. To support the users in multilingual communication, it is recognized that machine translation service used is not a perfect transparent-channel to users. We present agent metaphor as a novel interactive way to promote the efficiency of communication in using machine translation service. It will reduce the communication breaks caused by translation errors. We propose to shift from the transparent-channel metaphor to the agent metaphor, which motives the interactions between the users and the machine translator. Following this paradigm shifting, the agent should encourage the dialog participants to collaborate, as their interactivity will be helpful in reducing the number of translation errors. We examined the translation issues raised by multilingual communication, and analyzed the impact of interactivity on the elimination of translation errors. We proposed an implementation of the agent protocol for interactivity promotion. We designed the architecture of our agent, analyzed the interaction process, and provided an example of preparing repair strategy. We conducted an English–Chinese communication task experiment on tangram arrangement. The experiment shows that compared to the transparent-channel metaphor, our agent metaphor reduces human communication effort by 21.6%.

Chunqi Shi, Toru Ishida, Donghui Lin

Gaming for Language Services

Abstract

Service-oriented computing environments (SoCEs) such as the Language Grid can be regarded as the synthesis of their individual services. However, to make sustainable SoCEs, the user will want assurance that the billing structure is valid of and apportionment of cost burden among users is fair. To analyze the factors involved, we conduct donation and investment games for a machine translation service, where the service users participate in gaming. The results confirm the existence of users that actively try to make donations and social investments, users that remain passive to this kind of service, as well as users who tend to free ride on other users. Furthermore, we find that setting bonuses based on the total amount of donation and investment is effective in incentivizing some players to donate and invest. We also show how to reduce the cost of developing and executing gaming exercises for domain practitioners or experts. We define a game as a workflow of collaborative tasks executed by players. We develop game definition criteria to simplify game descriptions. We develop a gaming environment that enables web-based games to be implemented by using the game definitions.

Yuu Nakajima, Ryutaro Otsuka, Reiko Hishiyama, Takao Nakaguchi, Naoyuki Oda

Youth Mediated Communication: Knowledge Transfer as Intercultural Communication

Abstract

Transferring knowledge to other people in different languages is difficult because of gaps in languages and cultures. It makes the knowledge transfer more difficult when the recipient is young, because the comprehension and language ability of the young are incomplete. To better understand and design language services, this chapter introduces a communication protocol that meets requirements of agriculture support in rural areas, and fully delineates the communication environment by elucidating the field issues comprehensively; solutions are considered. The field experiment conducted involves agriculture support in Vietnam. In the context of agriculture support in rural areas, there exist several issues such as the requirement of timely knowledge transfer with high translation quality, and multilingual communication between youths and experts where gaps in language ability and expertise should be considered and addressed.

Toshiyuki Takasaki, Yumiko Mori, Toru Ishida, Masayuki Otani

Backmatter

Titel: Services Computing for Language Resources
herausgegeben von: Yohei Murakami
Donghui Lin
Toru Ishida
Verlag: Springer Singapore
Electronic ISBN: 978-981-10-7793-7
Print ISBN: 978-981-10-7792-0
DOI: https://doi.org/10.1007/978-981-10-7793-7