Learning to Predict Case Markers in Japanese

Proceedings of the 21st International Conference on Computational Linguistics and 44th Annual Meeting of the ACL, pages 1049–1056, Sydney, July 2006. c⃝2006 Association for Computational Linguistics Learning to Predict Case Markers in Japanese ����� ����� ����� ����� Hisami Suzuki Kristina Toutanova1 Microsoft Research One Microsoft Way, Redmond WA 98052 USA {hisamis,kristout}@microsoft.com Abstract Japanese case markers, which indicate the gram- matical relation of the complement NP to the predicate, often pose challenges to the generation of Japanese text, be it done by a foreign language learner, or by a machine translation (MT) system. In this paper, we describe the task of predicting Japanese case markers and propose machine learning methods for solving it in two settings: (i) monolingual, when given information only from the Japanese sentence; and (ii) bilingual, when also given information from a corresponding Eng- lish source sentence in an MT context. We formu- late the task after the well-studied task of English semantic role labelling, and explore features from a syntactic dependency structure of the sentence. For the monolingual task, we evaluated our models on the Kyoto Corpus and achieved over 84% ac- curacy in assigning correct case markers for each phrase. For the bilingual task, we achieved an ac- curacy of 92% per phrase using a bilingual dataset from a technical domain. We show that in both settings, features that exploit dependency informa- tion, whether derived from gold-standard annota- tions or automatically assigned, contribute signifi- cantly to the prediction of case markers.1 1 Introduction: why predict case? Generation of grammatical elements such as inflec- tional endings and case markers has become an impor- tant component technology, particularly in the context of machine translation (MT). In an English-to-Japanese MT system, for example, Japanese case markers, which indicate grammatical relations (e.g., subject, object, location) of the complement noun phrase to the predicate, are among the most difficult to generate appropriately. This is because the case markers often do not correspond to any word in the source language as many grammatical relations are expressed via word order in English. It is also difficult because the map- ping between the case markers and the grammatical 1 Author names arranged alphabetically relations they express is very complex. For the same reasons, generation of case markers is challenging to foreign language learners. This difficulty in generation, however, does not mean the choice of case markers is insignificant: when a generated sentence contains mis- takes in grammatical elements, they often lead to se- vere unintelligibility, sometimes resulting in a different semantic interpretation from the intended one. There- fore, having a model that makes reasonable predictions about which case marker to generate given the content words of a sentence, is expected to help MT and gen- eration in general, particularly when the source (or native) and the target languages are morphologically divergent. But how reliably can we predict case markers in Japanese using the information that exists only in the sentence? Consider the example in Figure 1. This sen- tence contains two case markers, kara …

Content truncated to 500 words