We address the problem of mining name transliterations from comparable corpora in languages P and Q in the following resource-poor scenario:Parallel names in PQ are not available for training. Parallel names in PR and RQ are available for training.We propose a novel solution for the problem by computing a common geometric feature space for P,Q and R where name transliterations are mapped to similar vectors. We employ Canonical Correlation Analysis (CCA) to compute the common geometric feature space using only parallel names in PR and RQ and without requiring parallel names in PQ. We test our algorithm on data sets in several languages and show that it gives results comparable to the state-of-the-art transliteration mining algorithms that use parallel names in PQ for training.

Machine transliteration is an important problem in an increasingly multilingual world, as it plays a critical role in many downstream applications, such as machine translation or crosslingual information retrieval systems. In this article, we propose compositional machine transliteration systems, where multiple transliteration components may be composed either to improve existing transliteration quality, or to enable transliteration functionality between languages even when no direct parallel names corpora exist between them. Specifically, we propose two distinct forms of composition: serial and parallel. Serial compositional system chains individual transliteration components, say, X → Y and Y → Z systems, to provide transliteration functionality, X → Z. In parallel composition evidence from multiple transliteration paths between X → Z are aggregated for improving the quality of a direct system. We demonstrate the functionality and performance benefits of the compositional methodology using a state-of-the-art machine transliteration framework in English and a set of Indian languages, namely, Hindi, Marathi, and Kannada. Finally, we underscore the utility and practicality of our compositional approach by showing that a CLIR system integrated with compositional transliteration systems performs consistently on par with, and sometimes better than, that integrated with a direct transliteration system.

No abstract available.

Address geocoding, the process of finding the map location for a structured postal address, is a relatively well-studied problem. In this paper we consider the more general problem of crosslingual location search, where the queries are not limited to postal addresses, and the language and script used in the search query is different from the one in which the underlying data is stored. To the best of our knowledge, our system is the first crosslingual location search system that is able to geocode complex addresses. We use a statistical machine transliteration system to convert location names from the script of the query to that of the stored data. However, we show that it is not sufficient to simply feed the resulting transliterations into a monolingual geocoding system, as the ambiguity inherent in the conversion drastically expands the location search space and significantly lowers the quality of results. The strength of our approach lies in its integrated, end-to-end nature: we use abstraction and fuzzy search (in the text domain) to achieve maximum coverage despite transliteration ambiguities, while applying spatial constraints (in the geographic domain) to focus only on viable interpretations of the query. Our experiments with structured and unstructured queries in a set of diverse languages and scripts (Arabic, English, Hindi and Japanese) searching for locations in different regions of the world, show full crosslingual location search accuracy at levels comparable to that of commercial monolingual systems. We achieve these levels of performance using techniques that may be applied to crosslingual searches in any language/script, and over arbitrary spatial data.

No abstract available.

Machine Transliteration deals with the conversion of text strings from one orthography to another, while preserving the phonetics of the strings in the two languages. Transliteration is an important problem in machine translation or cross-lingual information retrieval, as most proper names and generic iconic terms are out-of-vocabulary words, and therefore need to be transliterated. In this demo, we present Babel, a transliteration workbench, with generic statistical learning algorithms and a scripting engine to model the transliteration process. We demonstrate quick assembly of necessary components – algorithmic modules and training scripts – for systematic experimentation of transliteration tasks in a given pair of languages.

To effectively support today’s global economy, database systems need to manage data in multiple languages simultaneously. While current database systems do support the storage and management of multilingual data, they are not capable of querying across different natural languages. To address this lacuna, we have recently proposed two cross-lingual functionalities, LexEQUAL[13] and SemEQUAL[14], for matching multilingual names and concepts, respectively. In this paper, we investigate the native implementation of these multilingual functionalities as first-class operators on relational engines. Specifically, we propose a new multilingual storage datatype, and an associated algebra of the multilingual operators on this datatype. These components have been successfully implemented in the PostgreSQL database system, including integration of the algebra with the query optimizer and inclusion of a metric index in the access layer. Our experiments demonstrate that the performance of the native implementation is up to two orders-of-magnitude faster than the corresponding outsidethe- server implementation. Further, these multilingual additions do not adversely impact the existing functionality and performance. To the best of our knowledge, our prototype represents the first practical implementation of a crosslingual database query engine.

No abstract available.

Current database systems offer support for storing multilingual data, but are not capable of querying across languages, an important consideration in today's global economy. We therefore propose a new multilexical operator called LexEQUAL that extends the standard lexicographic matching in database systems to matching of text data across languages, specifically for names, which form close to twenty percent of text corpora. The implementation of the LexEQUAL operator is based on transforming matches in language space into parameterized approximate matches in the equivalent phoneme space. A detailed evaluation of our approach on a real data set shows that there exist settings of the algorithm parameters with which it is possible to achieve both good recall and precision.

No abstract available.