ABSTRACT Recently, translation scholars have made some general claims about translation propertie... more ABSTRACT Recently, translation scholars have made some general claims about translation properties. Some of these are source language independent while others are not. Koppel and Ordan (2011) performed empirical studies to validate both types of properties using English source texts and other texts translated into English. Ob- viously, corpora of this sort, which focus on a single language, are not adequate for claiming universality of translation properties. In this paper, we are validating both types of translation properties using origi- nal and translated texts from six European languages.
Readability classification is an important application of Natural Language Processing. It aims at... more Readability classification is an important application of Natural Language Processing. It aims at judging the quality of documents and to assist writers to identify possible problems. This paper presents a readability classifier for Bangla textbooks using information-theoretic and lexical features. All together 18 features are explored to achieve an F-score of 86.46%.
Machine translation systems always struggle transliterating names and unknown words during the tr... more Machine translation systems always struggle transliterating names and unknown words during the translation process. It becomes more problematic when the source and the target language use different scripts for writing. To handle this problem, transliteration systems are becoming popular as additional modules of the MT systems. In this abstract, we are presenting an English to Bangla name transliteration system that outperforms Google's transliteration system.
Abstract In this paper, we present an approach to language detection in streams of multilingual a... more Abstract In this paper, we present an approach to language detection in streams of multilingual ancient texts. We introduce a supervised classifier that detects, amongst others, Old High German (OHG) and Old Saxon (OS). We evaluate our model by means of three experiments that show that language detection is possible even for dead languages. Finally, we present an experiment in unsupervised language detection as a tertium comparationis for our supervised classifier.
I hereby declare that this thesis is based on the results found by myself. Materials of work foun... more I hereby declare that this thesis is based on the results found by myself. Materials of work found by other researcher are mentioned by reference. This thesis, neither in whole nor in part, has been previously submitted for any degree. ... I would like to thank my thesis advisor Dr. ...
ABSTRACT Recently, translation scholars have made some general claims about translation propertie... more ABSTRACT Recently, translation scholars have made some general claims about translation properties. Some of these are source language independent while others are not. Koppel and Ordan (2011) performed empirical studies to validate both types of properties using English source texts and other texts translated into English. Ob- viously, corpora of this sort, which focus on a single language, are not adequate for claiming universality of translation properties. In this paper, we are validating both types of translation properties using origi- nal and translated texts from six European languages.
Readability classification is an important application of Natural Language Processing. It aims at... more Readability classification is an important application of Natural Language Processing. It aims at judging the quality of documents and to assist writers to identify possible problems. This paper presents a readability classifier for Bangla textbooks using information-theoretic and lexical features. All together 18 features are explored to achieve an F-score of 86.46%.
Machine translation systems always struggle transliterating names and unknown words during the tr... more Machine translation systems always struggle transliterating names and unknown words during the translation process. It becomes more problematic when the source and the target language use different scripts for writing. To handle this problem, transliteration systems are becoming popular as additional modules of the MT systems. In this abstract, we are presenting an English to Bangla name transliteration system that outperforms Google's transliteration system.
Abstract In this paper, we present an approach to language detection in streams of multilingual a... more Abstract In this paper, we present an approach to language detection in streams of multilingual ancient texts. We introduce a supervised classifier that detects, amongst others, Old High German (OHG) and Old Saxon (OS). We evaluate our model by means of three experiments that show that language detection is possible even for dead languages. Finally, we present an experiment in unsupervised language detection as a tertium comparationis for our supervised classifier.
I hereby declare that this thesis is based on the results found by myself. Materials of work foun... more I hereby declare that this thesis is based on the results found by myself. Materials of work found by other researcher are mentioned by reference. This thesis, neither in whole nor in part, has been previously submitted for any degree. ... I would like to thank my thesis advisor Dr. ...
Uploads