Learning Phoneme Mappings for Transliteration without Parallel Data

Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the ACL, pages 37–45, Boulder, Colorado, June 2009. c⃝2009 Association for Computational Linguistics Learning Phoneme Mappings for Transliteration without Parallel Data Sujith Ravi and Kevin Knight University of Southern California Information Sciences Institute Marina del Rey, California 90292 {sravi,knight}@isi.edu Abstract We present a method for performing machine transliteration without any parallel resources. We frame the transliteration task as a deci- pherment problem and show that it is possi- ble to learn cross-language phoneme mapping tables using only monolingual resources. We compare various methods and evaluate their accuracies on a standard name transliteration task. 1 Introduction Transliteration refers to the transport of names and terms between languages with different writing sys- tems and phoneme inventories. Recently there has been a large amount of interesting work in this area, and the literature has outgrown being citable in its entirety. Much of this work focuses on back- transliteration, which tries to restore a name or term that has been transported into a foreign lan- guage. Here, there is often only one correct target spelling—for example, given jyon.kairu (the name of a U.S. Senator transported to Japanese), we must output “Jon Kyl”, not “John Kyre” or any other variation. There are many techniques for transliteration and back-transliteration, and they vary along a number of dimensions: • phoneme substitution vs. character substitution • heuristic vs. generative vs. discriminative mod- els • manual vs. automatic knowledge acquisition We explore the third dimension, where we see several techniques in use: • Manually-constructed transliteration models, e.g., (Hermjakob et al., 2008). • Models constructed from bilingual dictionaries of terms and names, e.g., (Knight and Graehl, 1998; Huang et al., 2004; Haizhou et al., 2004; Zelenko and Aone, 2006; Yoon et al., 2007; Li et al., 2007; Karimi et al., 2007; Sherif and Kondrak, 2007b; Goldwasser and Roth, 2008b). • Extraction of parallel examples from bilin- gual corpora, using bootstrap dictionaries e.g., (Sherif and Kondrak, 2007a; Goldwasser and Roth, 2008a). • Extraction of parallel examples from compara- ble corpora, using bootstrap dictionaries, and temporal and word co-occurrence, e.g., (Sproat et al., 2006; Klementiev and Roth, 2008). • Extraction of parallel examples from web queries, using bootstrap dictionaries, e.g., (Na- gata et al., 2001; Oh and Isahara, 2006; Kuo et al., 2006; Wu and Chang, 2007). • Comparing terms from different languages in phonetic space, e.g., (Tao et al., 2006; Goldberg and Elhadad, 2008). In this paper, we investigate methods to acquire transliteration mappings from non-parallel sources. We are inspired by previous work in unsupervised learning for natural language, e.g. (Yarowsky, 1995; 37 WFSA - A WFST - B English word sequence English sound sequence ( SPENCER ABRAHAM ) ( S P EH N S ER EY B R AH HH AE M ) WFST - C WFST - D Japanese sound sequence ( ス ペ ン サ ー ・ エ ー ブ ラ ハ ム ) Japanese katakana sequence ( S U P E N S A …

Content truncated to 500 words