Machine Translation
Shaalan, K., A. Abdel-Monem, A. Rafea, and H. Baraka,
"Mapping Interlingua Representations to Feature Structures of Arabic Sentences",
The Challenge of Arabic for NLP/MT International Conference, the British Computer Society, London, UK, British Computer Society (BCS), pp. 149–159, oct, 2006.
AbstractThe interlingua approach to Machine Translation (MT) aims to achieve the translation task in two independent steps. First, the meanings of source language sentences are represented in an intermediate (interlingua) representation. Then, sentences of the target language are generated from those meaning representations. In the generation of the target sentence, determining sentence structures becomes more difficult, especially when the interlingua does not contain any syntactic information. Hence, the sentence structures cannot be transferred exactly from the interlingua representations. In this paper, we present a mapping approach for taskoriented interlingua-based spoken dialogue that transforms an interlingua representation, so-called Interchange Format (IF), into a feature structure (FS) that reflects the syntactic structure of the target Arabic sentence. This approach addresses the handling of the problem of Arabic syntactic structure determination in the interlingua approach. A mapper is developed primarily within the framework of the NESPOLE! (NEgotiating through SPOken Language in E-commerce) multilingual speech-to-speech MT project. The IF-to-Arabic FS mapper is implemented in SICStus Prolog. Examples of Arabic syntactic mapping, using the output from the English analyzer provided by Carnegie Mellon University (CMU), will illustrate how the system works.
Nabhan, A., A. Rafea, and K. Shaalan,
"Enhancing Phrase Extraction from Word Alignments Using Morphology",
The 5th Conference on Language Engineering, Egyptian Society of Language Engineering (ELSE), Cairo, Egypt, Ain Shams University, pp. 57–65, sep, 2005.
AbstractWe propose a technique for effective extraction of bilingual phrases from word alignments using morphological processing. Morphological processing leads to an increase of the frequency of words in the corpus, consequently reduces Alignment Error Rate (AER). Intuitively, better word alignments enhance the quality of bilingual phrases extracted. Using alignments of a stemmed corpus for phrase extraction, instead of alignments of a raw one, shows significant improvements in translation quality, especially with small corpora.
Abdel-Monem, A., K. Shaalan, A. Rafea, and H. Baraka,
"A Proposed Approach for Generating Arabic from Interlingua in a Multilingual Machine Translation System",
Language Engineering conference, Cairo, Egypt, Ain Shams University, pp. 197–206, Oct, 2003.
AbstractIntelingua (meaning) representation has been successfully used in multilingual machine translation. This paper reports our attempt to generate Arabic sentence from interlingua. The proposed system will be compatible with the NESPOLE consortium. In NESPOLE an Interlingua called interchange format or IF, designed for travel planning is used. Our approach describes how to generate grammatically correct Arabic sentence from Interlingua. It involves two main components a mapper for converting intelingua into syntactic structure (feature-structure) and a generator for generating the target Arabic sentence that represents the intended meaning. A translation example is provided to explain the inner working of the system.
Shaalan, K.,
"Machine Translation of Arabic Interrogative Sentence into English",
the 8th International conference on Artificial Intelligence Applications, Cairo, Egypt, American University in Cairo, pp. 473–483, 2000.
AbstractThe present work reports our attempt in developing a bi-lingual Machine Translation (MT) tool in the agriculture domain. The work described here is part of an ongoing research to automate the translation of user interfaces of knowledge-based systems. In particular, we describe the translation of Arabic interrogative sentence into English. In Central Laboratory for Agricultural Expert Systems (CLAES), this tool is found to be essential in developing bilingual (Arabic-to-English) expert systems because both the Arabic and the English versions are needed for development and usage purpose. The tool follows the transfer-based MT approach. A major design goal of this tool is that it can be used as a stand-alone tool and can be very well integrated with a general MT system for Arabic sentence. The paper also describes our experience with the developed MT system and reports results of its application on interrogatives from real agricultural expert systems.