Multilingual Query Research Articles

PooRaa‐Agri KG: An agricultural knowledge graph‐based simplified multilingual query system

AbstractThe current work proposes PooRaa‐Agri KG, an agricultural knowledge graph‐based simplified multilingual query system that works in real time to provide concise answers for agriculture‐based queries. The proposed approach accommodates real‐time and low‐resource queries in English and Hindi with a novel multi‐stage solution consisting of data pre‐processing, sentence simplification, triplet extraction, knowledge graph generation, sentence reconstruction, query‐to‐reconstructed sentence matching, and machine translation as its sub‐modules. In this work, a novel combination of rule‐based sentence simplification and triplet extraction is carried out resulting in a triplet similarity score of 86.56% for the extracted triplets. This method is superior to the existing triplet extraction method whose triplet similarity score was found to be 60.65%. Further, the proposed work makes use of heuristic rules to reconstruct sentences which when evaluated by human evaluators for meaningfulness and grammar resulted in a score of 3.09/4 and 2.95/4 respectively. To complete end‐to‐end communication in the proposed system, a similarity‐based query answer system is proposed in this work.

Improving the representation of image descriptions for semantic image retrieval with RDF

The past few years have witnessed a surge of interest in many topics at the intersection of natural language processing and computer vision. In particular, using objects together with their attributes and relations to represent images or interpret languages has been proved useful across a wide variety of applications. The goal of this work is to provide an improved RDF-based model to represent images for enhancing textual based image retrieval. We use natural language processing tools to obtain a set of objects, attributes and relations; and then model them into graphical structures with RDF-based model. We also conduct some preliminary experiments to show how to handle textual based image retrieval for complex queries or multilingual queries. The experimental results show that our approach improves the representation of image descriptions, which is suitable for enhancing image retrieval with high-level semantics.

PADI-web: A multilingual event-based surveillance system for monitoring animal infectious diseases

Global animal disease outbreak detection and monitoring rely on official sources, such as intergovernmental organisations, as well as digital media and other unofficial outlets. Manually extracting relevant information from unofficial sources is time-consuming. The Platform for Automated extraction of animal Disease Information from the web (PADI-web) is an automated biosurveillance system devoted to online news source monitoring for the detection of emerging/new animal infectious diseases by the French Epidemic Intelligence System. The tool automatically collects news via customised multilingual queries, classifies them and extracts epidemiological information. We detail each step of the PADI-web pipeline, with a focus on the new user-oriented features.

Lost in translation? A multilingual Query Builder improves the quality of PubMed queries: a randomised controlled trial

BackgroundMEDLINE is the most widely used medical bibliographic database in the world. Most of its citations are in English and this can be an obstacle for some researchers to access the information the database contains. We created a multilingual query builder to facilitate access to the PubMed subset using a language other than English. The aim of our study was to assess the impact of this multilingual query builder on the quality of PubMed queries for non-native English speaking physicians and medical researchers.MethodsA randomised controlled study was conducted among French speaking general practice residents. We designed a multi-lingual query builder to facilitate information retrieval, based on available MeSH translations and providing users with both an interface and a controlled vocabulary in their own language. Participating residents were randomly allocated either the French or the English version of the query builder. They were asked to translate 12 short medical questions into MeSH queries. The main outcome was the quality of the query. Two librarians blind to the arm independently evaluated each query, using a modified published classification that differentiated eight types of errors.ResultsTwenty residents used the French version of the query builder and 22 used the English version. 492 queries were analysed. There were significantly more perfect queries in the French group vs. the English group (respectively 37.9% vs. 17.9%; p < 0.01). It took significantly more time for the members of the English group than the members of the French group to build each query, respectively 194 sec vs. 128 sec; p < 0.01.ConclusionsThis multi-lingual query builder is an effective tool to improve the quality of PubMed queries in particular for researchers whose first language is not English.

Cross-Lingual Topic Discovery From Multilingual Search Engine Query Log

Today, major commercial search engines are operating in a multinational fashion to provide web search services for millions of users who compose search queries by different languages. Hence, the search engine query log, which serves as the backbone of many search engine applications, records millions of users’ search history in a wide spectrum of human languages and demonstrates a strong multilingual phenomenon. However, with its salience, the multilingual nature of a search engine query log is usually ignored by existing works, which usually consider query log entries of different languages as being orthogonal and independent. This kind of oversimplified assumption heavily distorts the underlying structure of web search data. In this article, we pioneer in recognition of the multilingual nature of a query log and make the first attempt to cross the language barrier in query logs. We propose a novel model named Cross-Lingual Query Log Topic Model (CL-QLTM) to analyze query logs from a cross-lingual perspective and derive the latent topics of web search data. The CL-QLTM comprehensively integrates web search data in different languages by collectively utilizing cross-lingual dictionaries, as well as the co-occurrence relations in the query log. In order to relieve the efficiency bottleneck of applying the CL-QLTM on voluminous query logs, we propose an efficient parameter inference algorithm based on the MapReduce computing paradigm. Both qualitative and quantitative experimental results show that the CL-QLTM is able to effectively derive cross-lingual topics from multilingual query logs and spawn a wide spectrum of new search engine applications.

Enhanced Artificial Social Cockroaches (EASC) for Modern Information Retrieval

This article deals on an improved version of the recently developed Artificial Social Cockroaches (ASC) algorithm based on several modifications. The EASC has as input a set of artificial cockroaches and N selected shelters. It is based on a random displacement step and a set of operators (selection cockroaches, shelter attraction, congener's attraction, shelter permutation). Each cockroach must be hidden in the shelter where it feels safer (evaluation function). In the recent years with the coming of the world wide web, the amount of unstructured documents available in the digital society increases and becomes easily accessible, all this has led that satisfy the needs of users in terms of relevant information has become a substantial problem in the scientific community. The second component of the authors' study is to apply the algorithm (EASC) as an information retrieval system using multilingual pre-processing and thesaurus to solve the problems of multilingual query and searching with synonymy. The relevant documents will be rendered as a list of ranked and classified documents from the most relevant to the least relevant. Lastly the authors apply the benchmark Medline and a series of valuation measures (precision, recall, f-measure, entropy, error, accuracy, specificity, TCR, ROC) for the experimentation, also they have compared their results with the outcomes of set of existed systems (social worker bees, taboo search, genetic algorithm, simulating annealing, naïve method). The third component of the authors' system is the visualization step that ensures the presentation of the result in the form of a cobweb with some realism to be understandable by users.

Progress of the European Assistive Technology Information Network.

The European Assistive Technology Information Network (EASTIN), launched in 2005 as the result of a collaborative EU project, provides information on Assistive Technology products and related material through the website www.eastin.eu. In the past few years several advancements have been implemented on the EASTIN website thanks to the contribution of EU funded projects, including a multilingual query processing component for supporting non expert users, a user rating and comment facility, and a detailed taxonomy for the description of ICT based assistive products. Recently, within the framework of the EU funded project Cloud4All, the EASTIN information system has also been federated with the Unified Listing of assistive products, one of the building blocks of the Global Public Inclusive Infrastructure initiative.

Health, Food and User's Profile Ontologies for Personalized Information Retrieval

As we aim to retrieve personalized information to user's queries related to food, health and nutrition domains such as “Is apple good for people with heart diseases?”, “How much honey can be taken by a diabetic patient?”, “What are the health benefits of eating pineapple?” and “What are the fruits that contain the daily need quantity of calcium?” The information retrieval system needs to integrate ontologies from different domains such as food, nutrition, health (diseases, body parts, body functions) and recipe in order to answer such kind of queries. In addition, to support multilingual queries, the system and ontologies require aggregation of information from multi-level ontologies. Also, to achieve high relevancy and coverage we need to use ontologies that have comprehensive and rich vocabularies. Moreover, to make effective use for the annotation, ontologies concept names should be unique and self-contained. The main focus of this paper is to integrate ontologies from food, health and nutrition domains to help the personalized information systems to retrieve food and heath recommendations based on the user's health conditions and food preferences. Such ontologies that satisfy these requirements do not explicitly exist. Therefore, we were challenged to develop these ontologies by creating, integrating and reusing some of the existing ontologies to meet our requirements.

Multilingual query expansion in the SveMed+ bibliographic database: A case study

SveMed+ is a bibliographic database covering Scandinavian medical journals. It is produced by the University Library of Karolinska Institutet in Sweden. The bibliographic references are indexed with terms from the Medical Subject Headings (MeSH) thesaurus. The MeSH has been translated into several languages, including Swedish, making it suitable as the basis for multilingual tools in the medical field. The data structure of SveMed+ closely mimics that of PubMed/MEDLINE. Users of PubMed/MEDLINE and similar databases typically expect retrieval features that are not readily available off-the-shelf. The SveMed+ interface is based on a free text search engine (Solr) and a relational database management system (Microsoft SQL Server) containing the bibliographic database and a multilingual thesaurus database. The thesaurus database contains medical terms in three different languages and information about relationships between the terms. A combined approach involving the Solr free text index, the bibliographic database and the thesaurus database allowed the implementation of functionality such as automatic multilingual query expansion, faceting and hierarchical explode searches. The present paper describes how this was done in practice.

Detecting Multilingual and Multi-Regional Query Intent in Web Search

With rapid growth of commercial search engines, detecting multilingual and multi-regional intent underlying search queries becomes a critical challenge to serve international users with diverse language and region requirements. We introduce a query intent probabilistic model, whose input is the number of clicks on documents from different regions and in different language, while the output of this model is a smoothed probabilistic distribution of multilingual and multi-regional query intent. Based on an editorial test to evaluate the accuracy of the intent classifier, our probabilistic model could improve the accuracy of multilingual intent detection for 15%, and improve multi-regional intent detection for 18%. To improve web search quality, we propose a set of new ranking features to combine multilingual and multi-regional query intent with document language/region attributes, and apply different approaches in integrating intent information to directly affect ranking. The experiments show that the novel features could provide 2.31% NDCG@1 improvement and 1.81% NDCG@5 improvement.

Visualizing Cross-Lingual/Cross-Cultural Differences in Concerns in Multilingual Blogs

The goal of this paper is to cross-lingually analyze multilingual blogs collected with a topic keyword. The framework of collecting multilingual blogs with a topic keyword is designed as the blog feed retrieval procedure. Multilingual queries for retrieving blog feeds are created from Wikipedia entries. Finally, we present an interface for visualizing cross-lingual/cross-cultural differences in concerns and opinions that are closely related to a given topic. Preliminary evaluation results support the effectiveness of the proposed framework.

Mixed monolingual homepage finding in 34 languages: the role of language script and search domain

The information that is available or sought on the World Wide Web (Web) is increasingly multilingual. Information Retrieval systems, such as the freely available search engines on the Web, need to provide fair and equal access to this information, regardless of the language in which a query is written or where the query is posted from. In this work, we ask two questions: How do existing state of the art search engines deal with languages written in different alphabets (scripts)? Do local language-based search domains actually facilitate access to information? We conduct a thorough study on the effect of multilingual queries for homepage finding, where the aim of the retrieval system is to return only one document, namely the homepage described in the query. We evaluate the effect of multilingual queries in retrieval performance with regard to (i) the alphabet in which the queries are written (e.g., Latin, Russian, Arabic), and (ii) the language domain where the queries are posted (e.g., google.com, google.fr). We query four major freely available search engines with 764 queries in 34 different languages, and look for the correct homepage in the top retrieved results. In order to have fair multilingual experimental settings, we use an ontology that is comparable across languages and also representative of realistic Web searches: football premier leagues in different countries; the official team name represents our query, and the official team homepage represents the document to be retrieved. A series of thorough experiments involving over 10,000 runs, with queries both in their correct and in Latin characters, and also using both global-domain and local-domain searches, reveal that queries issued in the correct script of a language are more likely to be found and ranked in the top 3, while queries in non-Latin script languages which are however issued in Latin script are less likely to be found; also, queries issued to the correct local domain of a search engine, e.g., French queries to yahoo.fr, are likely to have better retrieval performance than queries issued to the global domain of a search engine. To our knowledge, this is the first Web retrieval study that uses such a wide range of languages.

Internationalized access to domain names: a review of methods and issues

PurposeThis article aims to understand the opportunities as well as the challenges posed by the methods for internationalized access to domain names.Design/methodology/approachThe paper first provides background information on how domain names are resolved in the domain name system (DNS). It then reviews the various methods for internationalized access to domain names with a focus on their technical implementation and potential problems. Finally, it discusses several important language and policy issues surrounding the methods.FindingsThe methods proposed for internationalized access to domain names can be classified into two groups: ASCII‐compatible encoding; and multilingual keywords. ASCII‐compatible encoding methods, such as the internationalized domain name (IDN) standards specified by the internet engineering task force, seem technically sound since they do not affect existing DNS operations, but they have some structural limitations. Multilingual keyword methods are rather simple and intuitive to use but they are not compatible with one another and so may return different results from the same multilingual keyword query. Also, both ASCII‐compatible encoding and multilingual keyword methods can raise some important issues associated with languages and policies, such as linguistic problems, disputes over IDNs, and multilingual homographs.Originality/valueThe issues discussed in this paper need to be addressed for broad and seamless implementation of the methods for internationalized access to domain names across various languages. The review of the methods and associated issues can prove helpful to those from internet users and domain name registrants to domain name registries and registrars.

Experimental Interfaces Involving Visual Grouping During Browsing

This paper provides a brief overview of a number of experimental interface design projects being carried out collaboratively by teams of researchers at the University of Alberta and elsewhere. One goal of this interface research is to explore the principles of rich-prospect browsing interfaces, which I have defined (Author 2003) as those where some meaningful representation of every item in a collection is combined with tools for manipulating the display. Often this manipulation is for the purposes of carrying out some portion of a research task: the interfaces lend themselves to exploratory and synthetic activities, such as knowledge discovery and hypothesis formulation. The projects summarized here begin with a browsing prototype originally designed for the task of pill identification (Given et al. 2005) but subsequently extended into a prototype for browsing conference delegates and other groups of people (Author et al. 2006). Another is a nuanced system based on the mandala (Cheypesh et al. 2006) intended for examining any collection that has been encoded with an XML schema, using combinations of attractors selected by the user from the available tags. Next is the set of specialized interfaces for the Orlando Project (Orlando Team 2006), intended to provide a set of discrete entry points into the deeply-encoded electronic history of women’s writing in the British Isles. Our project on tabular interfaces provides a variety of spaces designed to assist the user in using thesauri for multilingual query enhancement (Anvik et al. 2006). The final project described below is NORA (Unsworth 2004), which relies on the power of the D2K data-mining tools at the National Centre for Supercomputing Applications at the University of Illinois at Urbana-Champaign to give humanities scholars a workspace for exploring the system-identified features of common documents and further documents that have been recommended by the system. Each of these projects are discussed within the framework of visualizations involving browsing through dynamic grouping.

A Query Engine for Retrieving Information from Chinese HTML Documents

The amount of online information in Chinese and the number of Chinese Internet users have been increasing tremendously during the past decade. Since Chinese language is significantly different from English, techniques that have been developed for retrieving information from English Web documents cannot be directly applied to retrieve information from Chinese Web documents. In order to provide high-performance access of Chinese information on the Web, we have developed a Chinese Web query engine that (i) extracts (hierarchical) data of interest from Chinese HTML tables using an information extraction tool called semantic hierarchy, (ii) allows the user to submit queries in Chinese using a menu-driven user interface, and (iii) processes the user's queries (as Boolean expressions) to generate the correct results. Our query engine supports various groups of information that are categorized into various subject areas, such as car ads, house rentals, job ads, stocks, university catalogs, etc. We have tested our information extraction tool on two application domains, car-ads and house-rental. The average F-measure on extracting Chinese data from these two application domains is above 90%. More importantly, our query engine can easily be configured and internationalized to become a worldwide, multilingual query engine with minor changes in system settings on PCs running Windows operating systems.

Evaluating Chinese Text Retrieval with Multilingual Queries

This paper reports the design of a Chinese test collection with multilingual queries and the application of this test collection to evaluate information retrieval (IR) systems. The effective indexing units, IR models, translation techniques, and query expansion for Chinese text retrieval are identified. The collaboration of East Asian countries for construction of test collections for cross-language multilingual text retrieval is also discussed in this paper. As well, a tool is designed to help assessors judge relevance and gather the events of relevance judgment. The log file created by this tool will be used to analyze the behaviors of assessors in the future.

WWW-UDK

The environmental data catalogue Umweltdatenkatalog UDK is a standard meta-information system for environmental data for use by state authorities and the public. Technically, the UDK consists of a database together with a front-end tailored to the needs of environmental specialists. FZI's contribution has been to develop a front-end that makes the UDK database available using the tools and techniques of the World-Wide Web. Among the features of WWW-UDK are several query modes for the UDK objects and addresses, an environmental thesaurus, on-line access to some of the underlying data (e.g., databases and environmental reports), multilingual query and result forms, and an on-line help system. Currently, several installations of WWW-UDK are used in Austria and in Germany on the Internet and on Intranets. WWW-UDK can be easily integrated into a federation architecture which is based on CORBA, WWW, and Java.