Combination of Arabic Preprocessing Schemes for Statistical Machine Translation

Proceedings of the 21st International Conference on Computational Linguistics and 44th Annual Meeting of the ACL, pages 1–8, Sydney, July 2006. c⃝2006 Association for Computational Linguistics Combination of Arabic Preprocessing Schemes for Statistical Machine Translation Fatiha Sadat Institute for Information Technology National Research Council of Canada fatiha.sadat@cnrc-nrc.gc.ca Nizar Habash Center for Computational Learning Systems Columbia University habash@cs.columbia.edu Abstract Statistical machine translation is quite ro- bust when it comes to the choice of in- put representation. It only requires con- sistency between training and testing. As a result, there is a wide range of possi- ble preprocessing choices for data used in statistical machine translation. This is even more so for morphologically rich languages such as Arabic. In this paper, we study the effect of different word-level preprocessing schemes for Arabic on the quality of phrase-based statistical machine translation. We also present and evalu- ate different methods for combining pre- processing schemes resulting in improved translation quality. 1 Introduction Statistical machine translation (SMT) is quite ro- bust when it comes to the choice of input represen- tation. It only requires consistency between train- ing and testing. As a result, there is a wide range of possible preprocessing choices for data used in SMT. This is even more so for morphologically rich languages such as Arabic. We use the term “preprocessing” to describe various input modifi- cations applied to raw training and testing texts for SMT. Preprocessing includes different kinds of to- kenization, stemming, part-of-speech (POS) tag- ging and lemmatization. The ultimate goal of pre- processing is to improve the quality of the SMT output by addressing issues such as sparsity in training data. We refer to a specific kind of prepro- cessing as a “scheme” and differentiate it from the “technique” used to obtain it. In a previous pub- lication, we presented results describing six pre- processing schemes for Arabic (Habash and Sa- dat, 2006). These schemes were evaluated against three different techniques that vary in linguistic complexity; and across a learning curve of train- ing sizes. Additionally, we reported on the effect of scheme/technique combination on genre varia- tion between training and testing. In this paper, we shift our attention to exploring and contrasting additional preprocessing schemes for Arabic and describing and evaluating differ- ent methods for combining them. We use a sin- gle technique throughout the experiments reported here. We show an improved MT performance when combining different schemes. Similarly to Habash and Sadat (2006), the set of schemes we explore are all word-level. As such, we do not utilize any syntactic information. We define the word to be limited to written Modern Standard Arabic (MSA) strings separated by white space, punctuation and numbers. Section 2 presents previous relevant research. Section 3 presents some relevant background on Arabic linguistics to motivate the schemes dis- cussed in Section 4. Section 5 presents the tools and data sets used, along with the results of basic scheme experiments. Section 6 presents combina- tion techniques and their results. 2 Previous Work The anecdotal …

Content truncated to 500 words