Informatica

Spam reviews are a pervasive problem on online platforms due to its significant impact on reputation. However, research into spam detection in data streams is scarce. Another concern lies in their need for transparency. Consequently, this paper addresses those problems by proposing an online solution for identifying and explaining spam reviews, incorporating data drift adaptation. It integrates (i) incremental profiling, (ii) data drift detection & adaptation, and (iii) identification of spam reviews employing Machine Learning. The explainable mechanism displays a visual and textual prediction explanation in a dashboard. The best results obtained reached up to 87% spam F-measure.

In this paper, we propose a framework for extracting translation memory from a corpus of fiction and non-fiction books. In recent years, there have been several proposals to align bilingual corpus and extract translation memory from legal and technical documents. Yet, when it comes to an alignment of the corpus of translated fiction and non-fiction books, the existing alignment algorithms give low precision results. In order to solve this low precision problem, we propose a new method that incorporates existing alignment algorithms with proactive learning approach. We define several feature functions that are used to build two classifiers for text filtering and alignment. We report results on English-Lithuanian language pair and on bilingual corpus from 200 books. We demonstrate a significant improvement in alignment accuracy over currently available alignment systems.

In this paper, we describe a model for aligning books and documents from bilingual corpus with a goal to create “perfectly” aligned bilingual corpus on word-to-word level. Presented algorithms differ from existing algorithms in consideration of the presence of human translator which usage we are trying to minimize. We treat human translator as an oracle who knows exact alignments and the goal of the system is to optimize (minimize) the use of this oracle. The effectiveness of the oracle is measured by the speed at which he can create “perfectly” aligned bilingual corpus. By “Perfectly” aligned corpus we mean zero entropy corpus because oracle can make alignments without any probabilistic interpretation, i.e., with 100% confidence. Sentence level alignments and word-to-word alignments, although treated separately in this paper, are integrated in a single framework. For sentence level alignments we provide a dynamic programming algorithm which achieves low precision and recall error rate. For word-to-word level alignments Expectation Maximization algorithm that integrates linguistic dictionaries is suggested as the main tool for the oracle to build “perfectly” aligned bilingual corpus. We show empirically that suggested pre-aligned corpus requires little interaction from the oracle and that creation of perfectly aligned corpus can be achieved almost with the speed of human reading. Presented algorithms are language independent but in this paper we verify them with English–Lithuanian language pair on two types of text: law documents and fiction literature.

This paper examins approaches for translation between English and morphology-rich languages. Experiment with English–Russian and English–Lithuanian revels that “pure” statistical approaches on 10 million word corpus gives unsatisfactory translation. Then, several Web-available linguistic resources are suggested for translation. Syntax parsers, bilingual and semantic dictionaries, bilingual parallel corpus and monolingualWeb-based corpus are integrated in one comprehensive statistical model. Multi-abstraction language representation is used for statistical induction of syntactic and semantic transformation rules called multi-alignment templates. The decodingmodel is described using the feature functions, a log-linear modeling approach and A* search algorithm. An evaluation of this approach is performed on the English–Lithuanian language pair. Presented experimental results demonstrates that the multi-abstraction approach and hybridization of learning methods can improve quality of translation.

The paper offers a new way of presenting the structure of a sentence. None of the two widely known methods of representation the syntactic structure of a sentence can be of any avail when applied to the Lithuanian language. Neither the tree, based on the phrase structure principle, nor the tree, suggested by the dependency grammar, do reflect all the syntactic information, which a Lithuanian sentence contains.

High-quality machine translation between human languages has for a long time been an unattainable dream for many computer scientists involved in this fascinating and interdisciplinary field of the application of computers. The developed quite recently example-based machine translation technique seems to be a serious alternative to the existing automatic translation techniques. In the paper the usage of the example based machine translation technique for the development of system, which would be able to translate an unrestricted German text into Polish is proposed. The new approach to the example-based machine translation technique that takes into account the peculiarity of the Polish grammar is developed. The obtained primary results of the development of proposed system seem to be very promising and appear to be a step made in the right direction towards a fully-automatic high quality German-into-Polish machine translation system for unrestricted text.

Language engineering encompassing natural language processing and speech processing became very important for a development of every nation in multilingual Europe. After the Council of European Union approved conclucions on linguistic and cultural diversity, tools and systems created for every European language are necessary to overcome language barriers and to use all languages in various spheres of human cooperation. The paper gives an overview and a consideration of language engineering in Lithuania.