Shinichi Doi

Translation ambiguity resolution based on text corpora of source and target languages

We propose a new method to resolve ambiguity in translation and meaning interpretation using linguistic statistics extracted from dual corpora of source and target languages in addition to the logical restrictions described on dictionary and grammar rules for ambiguity resolution. It provides reasonable criteria for determining a suitable equivalent translation or meaning by making the dependency relation in the source language be reflected in the translated text. The method can be tractable because the required statistics can be computed semi-automatically in advance from a source language corpus and a target language corpus, while an ordinal corpus-based translation method needs a large volume of bilingual corpus of strict pairs of a sentence and its translation. Moreover, it also provides the means to compute the linguistic statistics on the pairs of meaning expressions.

Differentiated Incentive Rewarding for Social Networking Services

Our ultimate goal is to develop an information diffusion system where individuals are motivated to create content and share it with public. As our first step, in this paper, we present an incentive-rewarding mechanism for social networking services and focus particularly on changing reward assignment ratio considering different risks users perceive when uploading content with different privacy settings: public-open and friend-limited. Our learning-based simulation allowed us to observe enlargement of social networks with different rewarding ratio. The result also suggested that there is an optimal reward assignment ratio to maximize social networks.

NEC: description of the VENIEX system as used for MUC-5

NEC Corporation has had years of experience in natural language processing and machine translation[1, 2, 3, 4, 5], and currently markets commercial natural language processing systems. Utilizing dictionaries and parsing engines we have already had, we have developed the VENIEX System (VENus for Information EXtraction) as used for MUC-5 in only three months. Our method is to apply both domain-specific keyword-based analysis and full sentential parsing with general grammar[6, 7]. The keyword dictionary of VENIEX contains about thirty thousand entries, whose semantic structures are sub_ME_Capability frame, and the parsing and discourse processing are controlled with the information given in this semantic structure of keywords. The resulting scores of VENIEX for formal run texts were from 0.7181 (minimum) to 0.7548 (maximum) in Richness-Normalized Error and 48.33 in F-MEASURES (P&R).

Symbiotic technology for creating social innovation 30 years in the future

This paper discusses a way to create social innovation around 2040. With such innovation, social restrictions that are regarded as being inevitable in the current society can be eliminated. First, it is necessary to determine how to approach the innovation. Symbiotic technology is one of the promising technologies for achieving social innovation. It is the fusion of scientific technology and socio-technology. Its elemental technologies are classified into two categories: technologies for converging the real and cyber worlds and those for integrating hetero-systems. This paper describes examples of those technical categories and introduces the challenges of the first step toward social innovation.

An Interactive Translation Support Facility for Non-Professional Users

We present an interactive translation method to support non-professional users to write an original document. The method, combining dictionary lookup function and user-guided stepwise interactive machine translation, allows the user to obtain clear result with an easy operation. We implemented the method as an English writing support facility that serves as a translation support front-end to an arbitrary application.

Incentive Rewarding Method for Information Propagation in Social Networks

A problem in the social-network-based intaraction distribution is that people are less motivated to forward information when psychological forwarding cost is large. The simplest solution for this is to compensate for the cost by giving people incentive reward when they forward information. However, it is unclear that, even if we successfully propagate information over the whole social network by the incentive reward, this propagation is meaningful for the sender (original information source). Therefore, in this paper, we propose a novel incentive rewarding method where incentive reward is assigned to a forwarder only when the receiver reacts to the forwarded information. In our method, forwarders are motivated to attach their own recommendation comment when they forward information. As a result, our method can promote receivers to react the information without increasing the total amount of incentive reward, compared with the method that gives incentive reward independently of the receivers reaction.

Experiments on Personal Opinion Expression and Consensus Building using Future Chronicle

It is an important issue to understand the mechanism of personal opinion expression and consensus building in communities. We implemented an interactive application called ldquofuture chroniclerdquo for monitoring personal opinion expression and consensus building in communities. Future chronicle produces the field of personal opinion expression from multiple users, and users can share their thoughts with each other on this field. Moreover, we can observe the growth of communities through this application. In this paper, we report our experiments using future chronicle.

A Text Input Front-end Processor as an Information Access Platform

This paper presents a practical foreign language writing support tool which makes it much easier to utilize dictionary and example sentence resources. Like a Kana-Kanji conversion front-end processor used to input Japanese language text, this tool is also implemented as a front-end processor and can be combined with a wide variety of applications. A morphological analyzer automatically extracts key words from text as it is being input into the tool, and these words are used to locate information relevant to the input text. This information is then automatically displayed to the user. With this tool, users can concentrate better on their writing because much less interruption of their work is required for the consulting of dictionaries or for the retrieval of reference sentences. Retrieval and display may be conducted in any three ways: 1) relevant information is retrieved and displayed automatically; 2) information is retrieved automatically but displayed only on user command; 3) information is both retrieved and displayed only on user command. The extent to which the retrieval and display of information proceeds automatically depends on the type of information being referenced; this element of the design adds to system efficiency. Further, by combining this tool with a stepped-level interactive machine translation function, we have created a PC support tool to help Japanese people write in English.

Multi-user-type travel simulator based on open travel data

We have developed a simulator for evaluating changes in travel quality experienced during travel in multi-modal transit systems. The simulator has a new behavior model for users of multimodal systems that includes changes of user satisfaction, route and mode choices during travel, and interaction with on-line route guidance. This paper proposes a method for implementing user behavior models based on travel survey data, and describes an application example using open data for the city of Sydney.

Sharing risk-awareness for reliable resource management in smart buildings

Sustainable resource management using smart monitoring and control systems in large building complexes aims to achieve performance goals of tenants while reducing costs and reducing resource consumption. However conventional methods of optimizing resource use for normal activity may increase susceptibility to internal or external system failures. We present a cooperative approach to resource management in multi-tenant buildings that includes sharing of risk awareness and show that it is effective for increasing the reliability of resource supply for all tenants.