Rule Filtering by Pattern for Efficient Hierarchical Translation

Proceedings of the 12th Conference of the European Chapter of the ACL, pages 380–388, Athens, Greece, 30 March – 3 April 2009. c⃝2009 Association for Computational Linguistics Rule Filtering by Pattern for Efficient Hierarchical Translation Gonzalo Iglesias⋆ Adri`a de Gispert‡ ⋆ University of Vigo. Dept. of Signal Processing and Communications. Vigo, Spain {giglesia,erbanga}@gts.tsc.uvigo.es ‡ University of Cambridge. Dept. of Engineering. CB2 1PZ Cambridge, U.K. {ad465,wjb31}@eng.cam.ac.uk Eduardo R. Banga⋆ William Byrne‡ Abstract We describe refinements to hierarchical translation search procedures intended to reduce both search errors and memory us- age through modifications to hypothesis expansion in cube pruning and reductions in the size of the rule sets used in transla- tion. Rules are put into syntactic classes based on the number of non-terminals and the pattern, and various filtering strate- gies are then applied to assess the impact on translation speed and quality. Results are reported on the 2008 NIST Arabic-to- English evaluation task. 1 Introduction Hierarchical phrase-based translation (Chiang, 2005) has emerged as one of the dominant cur- rent approaches to statistical machine translation. Hiero translation systems incorporate many of the strengths of phrase-based translation systems, such as feature-based translation and strong tar- get language models, while also allowing flexi- ble translation and movement based on hierarchi- cal rules extracted from aligned parallel text. The approach has been widely adopted and reported to be competitive with other large-scale data driven approaches, e.g. (Zollmann et al., 2008). Large-scale hierarchical SMT involves auto- matic rule extraction from aligned parallel text, model parameter estimation, and the use of cube pruning k-best list generation in hierarchical trans- lation. The number of hierarchical rules extracted far exceeds the number of phrase translations typ- ically found in aligned text. While this may lead to improved translation quality, there is also the risk of lengthened translation times and increased memory usage, along with possible search errors due to the pruning procedures needed in search. We describe several techniques to reduce mem- ory usage and search errors in hierarchical trans- lation. Memory usage can be reduced in cube pruning (Chiang, 2007) through smart memoiza- tion, and spreading neighborhood exploration can be used to reduce search errors. However, search errors can still remain even when implementing simple phrase-based translation. We describe a ‘shallow’ search through hierarchical rules which greatly speeds translation without any effect on quality. We then describe techniques to analyze and reduce the set of hierarchical rules. We do this based on the structural properties of rules and develop strategies to identify and remove redun- dant or harmful rules. We identify groupings of rules based on non-terminals and their patterns and assess the impact on translation quality and com- putational requirements for each given rule group. We find that with appropriate filtering strategies rule sets can be greatly reduced in size without im- pact on translation performance. 1.1 Related Work The search and rule pruning techniques described in the following sections add to a growing lit- erature of refinements to the hierarchical phrase- based SMT systems originally …

Content truncated to 500 words