Multilingual document clustering : state of the art Multilingual corpora are extensively exploited in several branches of natural language processing. This paper presents an overview of works in the automatic construction of such corpora. We address this topic by first providing an overview of different perceptions of comparability. We then examine the main approaches to similarity computation,...

Parallel corpus is a rich linguistic resource for various multilingual text management tasks, including crosslingual text retrieval, multilingual computational linguistics and multilingual text mining. Constructing a parallel corpus requires effective alignment of parallel documents. In this paper, we develop a parallel page identification system for identifying and aligning parallel documents ...

Hierarchical attention networks have recently achieved remarkable performance for document classification in a given language. However, when multilingual document collections are considered, training such models separately for each language entails linear parameter growth and lack of cross-language transfer. Learning a single multilingual model with fewer parameters is therefore a challenging b...

Universal Networking Language (UNL) is a language for computer to represent knowledge and information described in natural languages. Universal Words (UWs) constitute the vocabulary of UNL. The UNL Explorer is a web based application, which combines all the components of UNL system to be accessible online. The users of UNL Explorer are not only researchers and linguists who are interested to wo...

In this paper, a multilingual acoustic model set derived from English, Hindi, and Spanish is utilised to recognise speech in Indonesian. In order to achieve this task we incorporate a two tiered approach to perform the cross-lingual porting of the multilingual models to a new language. In the first stage, we use an entropy based decision tree to merge similar phones from different languages int...

This paper reports on the first usage of the MultiFarm dataset for evaluating ontology matching systems. This dataset has been designed as a comprehensive benchmark for multilingual ontology matching. In this first set of experiments, we analyze how state-of-the-art matching systems – not particularly designed for the task of multilingual ontology matching – perform on this dataset. Our experim...

Multilingual software development is put in limelight due to the globalization efforts of the organization. But these development approaches do not have any reference model or framework from the language perspective. This situation limits multilingual software development. In order to address this, we developed architectural reference model for multilingual software (ARMMS) using unit operation...

In this paper, we investigate Multilingual Stacked Bottleneck Features (SBN) in language recognition domain. These features are extracted using bottleneck neural networks trained on data from multiple languages. Previous results have shown benefits of multilingual training of SBN feature extractor for speech recognition. Here we focus on its impact on language recognition. We present results ob...

Subjectivity analysis has received increasing attention in natural language processing field. Most of the subjectivity analysis works however are conducted on single languages. In this paper, we propose to perform multilingual subjectivity analysis by combining multi-view learning and AdaBoost techniques. We aim to show that by boosting multi-view classifiers we can develop more effective multi...

We present three approaches to word sense disambiguation that use Wikipedia as a source of sense annotations. Starting from a basic monolingual approach, we develop two multilingual systems: one that uses a machine translation system to create multilingual features, and one where multilingual features are extracted primarily through the interlingual links available in Wikipedia. Experiments on ...