Cross-language and Cross-encyclopedia Article Linking Using Mixed-language Topic Model and Hypernym Translation

Purpose With the increasing number of online multilingual resources, cross-language information retrieval (CLIR) has drawn much attention from the information retrieval (IR) research community. However, few studies have examined how and why multilingual searchers seek information in two or more languages, specifically how they switch and mix language in queries to get satisfying results. The purpose of this paper is to focus on Chinese–English bilinguals’ intra-sentential code-switching behaviors in online searches. The scenarios and reasons of code-switching, factors that may affect code-switching, the patterns of mixed language query formulation and reformulation and how current IR systems and other search tools can facilitate such information needs were examined. Design/methodology/approach In-depth semi-structured interviews were used as the research method. In total, 30 participants were recruited based on their English proficiency, location and profession, using a purposive sampling method. Findings Four scenarios and four reasons for using Chinese–English mixed language queries to cover information needs were identified, and results suggest that linguistic and cultural/social factors are of equivalent importance in code-switching behaviors. English terms and Chinese terms in queries play different roles in searches, and mixed language queries are irreplaceable by either single language queries or other search facilitating features. Findings also suggest current search engines and tools need greater emphasis in the user interface and more user education is required. Originality/value This study presents a qualitative analysis of bilinguals’ code-switching behaviors in online searches. Findings are expected to advance the theoretical understanding of bilingual users’ search strategies and interactions with IR systems, and provide insights for designing more effective IR systems and tools to discover multilingual online resources, including cross-language controlled vocabularies, personalized CLIR tools and mixed language query assistants.

Download Full-text

Regularization of multilingual topic models

Numerical Methods and Programming (Vychislitel'nye Metody i Programmirovanie) ◽

10.26089/nummet.v16r104 ◽

2015 ◽

pp. 26-38

Author(s):

М.А. Дударенко

Keyword(s):

Topic Model ◽

Information Source ◽

Topic Models ◽

Bilingual Dictionary ◽

Bilingual Dictionaries ◽

Probabilistic Topic Model ◽

Word Translation ◽

Cross Lingual ◽

Cross Language

Предлагается многоязычная вероятностная тематическая модель, одновременно учитывающая двуязычный словарь и связи между документами параллельной или сравнимой коллекции. Для комбинирования этих двух видов информации применяется аддитивная регуляризация тематических моделей (ARTM). Предлагаются два способа использования двуязычного словаря: первый учитывает только сам факт связи между словами--переводами, во втором настраиваются вероятности переводов в каждой теме. Качество многоязычных моделей измеряется на задаче кросс-язычного поиска, когда запросом является документ на одном языке, а поиск производится среди документов другого языка. Показано, что комбинированный учет слов--переводов из двуязычного словаря и связанных документов улучшает качество кросс-язычного поиска по сравнению с моделями, использующими только один тип информации. Сравнение разных методов включения в модель двуязычных словарей показывает, что оценивание вероятностей переводов не только улучшает качество модели, но и позволяет находить тематический контекст для пар слово--перевод. A multilingual probabilistic topic model based on the additive regularization ARTM allowing to combine both a parallel or comparable corpus and a bilingual translation dictionary is proposed. Two approaches to include information from a bilingual dictionary are discussed: the first one takes into account only the fact of connection between word translations, whereas the second one learns the translation probabilities for each topic. To measure the quality of the proposed multilingual topic model, a cross-language search is performed. For each query document in one language, it is found its translation on another language. It is shown that the combined translation of words from a bilingual dictionary and the corresponding connected documents improves the cross-lingual search compared to the models using only one information source. The use of learning word translation probabilities for bilingual dictionaries improves the quality of the model and allows one to determine a context (a set of topics) for each pair of word translations, where these translations are appropriate.

Download Full-text

Tibetan-Chinese Cross Language Text Similarity Calculation Based on LDA Topic Model

The Open Cybernetics & Systemics Journal ◽

10.2174/1874110x01509012911 ◽

2015 ◽

Vol 9 (1) ◽

pp. 2911-2919 ◽

Cited By ~ 2

Author(s):

Sun Yuan ◽

Zhao Qian

Keyword(s):

Topic Model ◽

Text Similarity ◽

Similarity Calculation ◽

Cross Language ◽

Language Text

Download Full-text

Psychometric Parameters of the Spanish Version of the Kuwait University Anxiety Scale (S-KUAS)1

European Journal of Psychological Assessment ◽

10.1027/1015-5759.20.4.349 ◽

2004 ◽

Vol 20 (4) ◽

pp. 349-357 ◽

Cited By ~ 28

Author(s):

Ahmed M. Abdel-Khalek ◽

Joaquin Tomás-Sabádo ◽

Juana Gómez-Benito

Keyword(s):

Reliability And Validity ◽

Anxiety Scale ◽

Spanish Version ◽

Good Reliability ◽

Kuwait University ◽

Males And Females ◽

Anxiety Levels ◽

Arabic And English ◽

Cross Language ◽

Language Equivalence

Summary: To construct a Spanish version of the Kuwait University Anxiety Scale (S-KUAS), the Arabic and English versions of the KUAS have been separately translated into Spanish. To check the comparability in terms of meaning, the two Spanish preliminary translations were thoroughly scrutinized vis-à-vis both the Arabic and English forms by several experts. Bilingual subjects served to explore the cross-language equivalence of the English and Spanish versions of the KUAS. The correlation between the total scores on both versions was .93, and the t value was .30 (n.s.), denoting good similarity. The Alphas and 4-week test-retest reliabilities were greater than .84, while the criterion-related validity was .70 against scores on the trait subscale of the STAI. These findings denote good reliability and validity of the S-KUAS. Factor analysis yielded three high-loaded factors of Behavioral/Subjective, Cognitive/Affective, and Somatic Anxiety, equivalent to the original Arabic version. Female (n = 210) undergraduates attained significantly higher mean scores than their male (n = 102) counterparts. For the combined group of males and females, the correlation between the total score on the S-KUAS and age was -.17 (p < .01). By and large, the findings of the present study provide evidence of the utility of the S-KUAS in assessing trait anxiety levels in the Spanish undergraduate context.

Download Full-text