Books are silent ambassadors: The Noma award for the translation of Japanese literature

Summary Now more than ever good translations are proving to be vitally important to fulfilling Shoichi Noma’s mission of advancing good relationships between cultures. With the emergence of dozens of world-class Japanese writers, the translators of Japanese literature have acquired a new significance and a new importance. No longer are they required to simply handle the language like an exotic and precious commodity but they must prepare a writer’s work to compete with literature from around the globe and let others understand the issues at their very heart of the Japanese people. Indeed, the selection committee’s choice of Murakami’s Wind-Up Bird Chronicle is an apt example of how literature at its very best can span cultural divides to promote mutual understanding of very complicated and important world issues. Written for Japanese to help them understand the devastation of war, it is a rare and timely book that confronts Japan’s experience head on. Ironically, Noma’s idea that books are silent ambassadors, an idea born from agony and defeat, so many years later is helping the world come together towards a unified vision of peace and understanding. “Literature has been described as a means of exchange between the hearts of people. Literary translation, then, is the building of bridges so that all peoples of the world can interact in this way.” Ye Weiqu, Chinese Institute of Social Studies.     

Character N-Gram Tokenization for European Language Text Retrieval

The Cross-Language Evaluation Forum has encouraged research in text retrieval methods for numerous European languages and has developed durable test suites that allow language-specific techniques to be investigated and compared. The labor associated with crafting a retrieval system that takes advantage of sophisticated linguistic methods is daunting. We examine whether language-neutral methods can achieve accuracy comparable to language-specific methods with less concomitant software complexity. Using the CLEF 2002 test set we demonstrate empirically how overlapping character n-gram tokenization can provide retrieval accuracy that rivals the best current language-specific approaches for European languages. We show that n = 4 is a good choice for those languages, and document the increased storage and time requirements of the technique. We report on the benefits of and challenges posed by n-grams, and explain peculiarities attendant to bilingual retrieval. Our findings demonstrate clearly that accuracy using n-gram indexing rivals or exceeds accuracy using unnormalized words, for both monolingual and bilingual retrieval.     

Analysis of Statistical Question Classification for Fact-Based Questions

Question classification systems play an important role in question answering systems and can be used in a wide range of other domains. The goal of question classification is to accurately assign labels to questions based on expected answer type. Most approaches in the past have relied on matching questions against hand-crafted rules. However, rules require laborious effort to create and often suffer from being too specific. Statistical question classification methods overcome these issues by employing machine learning techniques. We empirically show that a statistical approach is robust and achieves good performance on three diverse data sets with little or no hand tuning. Furthermore, we examine the role different syntactic and semantic features have on performance. We find that semantic features tend to increase performance more than purely syntactic features. Finally, we analyze common causes of misclassification error and provide insight into ways they may be overcome.