There has been an increase in the amount of multilingual text on the Internet due to the proliferation of news sources and blogs. The Urdu language, in particular, has experienced explosive growth on the Web. Text mining for information discovery, which includes tasks such as identifying topics, relationships and events, and sentiment analysis, requires sophisticated natural language processing (NLP). NLP systems begin with modules such as word segmentation, part-of-speech tagging, and morphological analysis and progress to modules such as shallow parsing and named entity tagging. While there have been considerable advances in developing such comprehensive NLP systems for English, the work for Urdu is still in its infancy. The tasks of interest in Urdu NLP includes analyzing data sources such as blogs and comments to news articles to provide insight into social and human behavior. All of this requires a robust NLP system. The objective of this work is to develop an NLP infrastructure for Urdu that is customizable and capable of providing basic analysis on which more advanced information extraction tools can be built. This system assimilates resources from various online sources to facilitate improved named entity tagging and Urdu-to-English transliteration. The annotated data required to train the learning models used here is acquired by standardizing the currently limited resources available for Urdu. Techniques such as bootstrap learning and resource sharing from a syntactically similar language, Hindi, are explored to augment the available annotated Urdu data. Each of the new Urdu text processing modules has been integrated into a general text-mining platform. The evaluations performed demonstrate that the accuracies have either met or exceeded the state of the art.

An essential tool in object oriented modeling is the specification of cardinalities of associations between classes. In Object Constraint Language (OCL) such constraints are expressed as conditions on the sizes of the collections that correspond to associations. In this paper we present tools and techniques for automated verification of size properties of collection types in OCL. We automatically verify invariants related to the sizes of the collections of a class with respect to the pre and post-conditions of the methods of that class. Our approach is based on a size abstraction that abstracts away the contents of the collections, but preserves the constraints on their sizes. We implemented a tool which automates this abstraction by converting OCL expressions on collections to arithmetic expressions on their sizes. Following this translation, we employ an infinite state model checker, called Action Language Verifier (ALV), for size analysis. Size abstraction reduces the state space of the system and, hence, the cost of automated verification, and by focusing on size properties, enables us to use efficient, domain specific model checking techniques for automated verification. To demonstrate the effectiveness of our approach we conducted a case study on the OCL specification of the Java Card API. The OCL specification of the Java Card API consists of 31 classes and 150 methods. Using our tool, we translated the OCL specification of each class to Action Language and verified the size properties using ALV. Verification with ALV took only a few seconds per class and we revealed errors in 26 out of the 150 method specifications.

We describe an experiment designed to evaluate the capabilities of our trainable transfer-based (Xfer) machine translation approach, as applied to the task of Hindi-to-English translation, and trained under an extremely limited data scenario. We compare the performance of the Xfer approach with two corpus-based approaches---Statistical MT (SMT) and Example-based MT (EBMT)---under the limited data scenario. The results indicate that the Xfer system significantly outperforms both EBMT and SMT in this scenario. Results also indicate that automatically learned transfer rules are effective in improving translation performance, compared with a baseline word-to-word translation version of the system. Xfer system performance with a limited number of manually written transfer rules is, however, still better than the current automatically inferred rules. Furthermore, a "multiengine" version of our system that combined the output of the Xfer and SMT systems and optimizes translation selection outperformed both individual systems.