Feature representations extracted from deep neural networkbased multilingual frontends provide significant improvements to speech recognition systems in low resource settings. To effectively train these frontends, we introduce a data selection technique that discovers language groups from an available set of training languages. This data selection method reduces the required amount of training ...

Multilingual computing is going to dominate the next era of Information Technology. Many Multilingual products are available in the market today. But, unfortunately most of the products are font based and not language based. We know that the E-mail facility is now being used extensively. But, unfortunately the usage of E-mail is limited within the people who know English. Even though some E-mai...

The task of multilingual summarization aims to design free-from language systems. Extractive methods are in the core of multilingual summarization systems. In this paper, we discuss the influence of various basic NLP tasks: sentence splitting, tokenization, stop words removal and stemming on sentence scoring and summaries' coverage. Hence, we propose a statistical method which extracts most rel...

This paper focuses on how automatic translation techniques integrated in a patent retrieval system increase its capabilities and make possible extended features and functionalities. We describe 1) a novel methodology for natural language to SPARQL translation based on a grammar–ontology interoperability automation and a query grammar for the patents domain; 2) a devised strategy for statistical...

The growth of multilingual web content and increasing internationalization portends the need for cross-language query processing. We offer ML-OntoES (a MultiLingual Ontology-based Extraction System) as a solution for narrowdomain/data-rich applications. Based on language-independent extraction ontologies (Embley, Liddle, & Lonsdale, 2011), ML-OntoES enables semantic search over domain-specific,...

We propose a corpus-based probabilistic framework to extract hidden common syntax across languages from non-parallel multilingual corpora in an unsupervised fashion. For this purpose, we assume a generative model for multilingual corpora, where each sentence is generated from a language dependent probabilistic contextfree grammar (PCFG), and these PCFGs are generated from a prior grammar that i...

This document overviews the strategy, effort and aftermath of the MultiLing 2013 multilingual summarization data collection. We describe how the Data Contributors of MultiLing collected and generated a multilingual multi-document summarization corpus on 10 different languages: Arabic, Chinese, Czech, English, French, Greek, Hebrew, Hindi, Romanian and Spanish. We discuss the rationale behind th...

This document overviews the strategy, effort and aftermath of the MultiLing 2013 multilingual summarization data collection. We describe how the Data Contributors of MultiLing collected and generated a multilingual multi-document summarization corpus on 10 different languages: Arabic, Chinese, Czech, English, French, Greek, Hebrew, Hindi, Romanian and Spanish. We discuss the rationale behind th...

We introduce phylogenetic and areal language features to the domain of multilingual text-to-speech synthesis. Intuitively, enriching the existing universal phonetic features with crosslingual shared representations should benefit the multilingual acoustic models and help to address issues like data scarcity for low-resource languages. We investigate these representations using the acoustic mode...

How to find needed information from the web is a critical issue in the Internet. Fortunately, search engines are useful tool to retrieve information from Internet. Although, Internet users speak different languages most of resources are written and published in the English. All Internet search engines provide a lingual search, although some of them enable the searcher to select the language of ...