Applying Machine Translation Evaluation Techniques to Textual CBR

Adeyanju, Ibrahim; Wiratunga, Nirmalie; Lothian, Robert; Craw, Susan

doi:10.1007/978-3-642-14274-1_4

Cited by 3 publications

(4 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Traditionally, human judgment is used in evaluating MT systems based on two main criteria: adequacy and fluency. Human judgment of the MT output is expensive and subjective therefore, automatic evaluation measures are a necessity (Adeyanju et al, 2010). There are various methods used in evaluating MT systems.…”

Section: Evaluation Of Machine Translationmentioning

confidence: 99%

Approaches to Machine Translation: A Review

et al. 2016

Self Cite

View full text Add to dashboard Cite

Translation is the transfer of the meaning of a text from one language to another. It is a means of sharing information across languages and therefore essential for addressing information inequalities. The work of translation was originally carried out by human translators and its limitations led to the development of machine translators. Machine Translation is a subfield of computational linguistics that investigates the use of computer software to translate text or speech from one natural language to another. There are different approaches to machine translation. This paper reviews the two major approaches (single vs. hybrid) to machine translation and provides critique of existing machine translation systems with their merits and demerits. Several application areas of machine translation and various methods used in evaluating them were also discussed. Our conclusion from the reviewed literatures is that a single approach to machine translation fails to achieve satisfactory performance resulting in lower quality and fluency of the output. On the other hand, a hybrid approach combines the strength of two or more approaches to improve the overall quality and fluency of the translation.

show abstract

Section: Evaluation Of Machine Translationmentioning

confidence: 99%

Approaches to Machine Translation: A Review

et al. 2016

Self Cite

View full text Add to dashboard Cite

show abstract

“…Though such reports are mostly used currently for auditing and tracking purposes, it is easy to see that they provide a wealth of information that could be exploited in knowledge reuse systems such as Case-Based Reasoning 2 . CBR systems make use of problemsolution repositories to find possible solutions to new problems.…”

Section: School Reports Continuing Difficulties With Repetitive Questmentioning

confidence: 99%

“…Research in CBR focusses on improving the mechanisms to retrieve similar problems, reuse their solutions by adapting to solve the new problem, revise the adapted solution based on the new problem, and retain the new solution by storing it in the repository. In addition to the large recent interest in textual CBR [16,2,10], there has been a good amount of work in improving retrieval in textual question answer repositories [24,11] of late, mostly from the information retrieval community. Usage of translation models to model question-answer vocabulary correlations was first explored in [6].…”

Section: Related Workmentioning

confidence: 99%

Two-part segmentation of text documents

Deepak

Visweswariah

Wiratunga

et al. 2012

Proceedings of the 21st ACM International Conference on Information and Knowledge Management

Self Cite

View full text Add to dashboard Cite

“…Assessments also are used to identify individual student weaknesses and strengths so that educators can provide specialized academic support, educational programming, or social services. In addition, assessments are developed by a wide array of groups and individuals, including teachers, district administrators, universities, private companies, state departments of education, and groups that include a combination of these individuals and institutions.Assessment of students' ability and understanding of various course concepts have been done using tools such as paper based test and computer based test (Adeyanju, Wiratunga, Recio_Garcia and Lothian, 2010).…”

Section: Introductionmentioning

confidence: 99%