In this paper we present an architecture for generating texts that vary in the emphasis put on conciseness, readability and the marking of particularly salient items. We abandon the traditional pipeline architecture, and use an integrated approach which makes the search for an optimum text explicit, taking into account both inter-sentential and intra-sentential features. We describe a context s...

The first step in most empirical work in multilingual NLP is to construct maps of the correspondence between texts and their translations (bitext maps). The Smooth Injective Map Recognizer (SIMR) algorithm presented here is a generic pattern recognition algorithm that is particularly well-suited to mapping bitext correspondence. SIMR is faster and significantly more accurate than other algorith...

Sentence Boundary Detection (SBD) is a very important prerequisite for proper sentence analysis in different Natural Language Processing tasks. During the last years, many SBD methods have been used in the transcriptions produced by Automatic Speech Recognition systems and in well-structured texts (e.g. news, scientific texts). However, there are few researches about SBD in informal user-genera...

Social media has become almost ubiquitous in present times. Such proliferation leads to automatic information processing need and has various challenges. The nature of social media content is mostly informal. Additionally while talking about Indian social media, users often prefer to use Roman transliterations of their native languages and English embedding. Therefore Information retrieval (IR)...

This article realized the Russian way of theological media education literacy and hermeneutic analysis of specific examples of Soviet anti-religious audiovisual media texts: a study of the process of interpretation of these media texts, cultural and historical factors influencing the views of the media agency / authors. The hermeneutic analysis suggests media text comprehension through comparis...

We discuss ongoing work on developing tools and techniques for understanding natural-language descriptions of security and privacy rules, particularly in the context of cloud computing services. In particular, we present a three-part toolkit for analyzing and processing texts, and enforcing privacy and security rules extracted from those texts. We are interested in developing efficient, accurat...

Ordering information is a critical task for natural language generation applications. In this paper we propose an approach to information ordering that is particularly suited for text-to-text generation. We describe a model that learns constraints on sentence order from a corpus of domainspecific texts and an algorithm that yields the most likely order among several alternatives. We evaluate th...

This research suggests a method for machine translation among two Kurdish dialects. We chose the two widely spoken dialects, Kurmanji and Sorani, which are considered to be mutually unintelligible. Also, despite being spoken by about 30 million people in different countries, Kurdish is among less-resourced languages. The research used bi-dialectal dictionaries and showed that the lack of parall...

In this contribution, we present a computational stylistic study of the French classic literature texts based on a data-driven approach where discovering interesting linguistic patterns is done without any prior knowledge. We propose an objective interestingness measure to extract meaningful stylistic syntactic patterns from a given author’s work. Our hypothesis is based on the fact that the mo...

Advances in text analysis, particularly the ability to extract network based information from texts, is enabling researches to conduct detailed socio-cultural ethnographies rapidly by retrieving characteristic descriptions from texts and fusing the results from varied sources. We describe this process and illustrate it in the context of conflict in the Sudan. We show how network information can...