Automatic Identification of Zero Pronouns and their Antecedents within Aligned Sentence Pairs

This paper proposes a method to identify zero pronouns within a ~]apansse sentence and their antecedent equivalents within the corresponding English sentence from aligned sentence pairs. The method focuses on the characteristics of Japanese and English, in two languages from cHfBerent f~rngles and in which distribution of zero pronouns is very d.uTerent. In this method, the Japanese sentence and English translation within the Japanese and English aligned sentence pairs are analyzed. Then, the pairs of Japanese word/phrase and their English equivalent word/phrase are identified from each aligned sentence pair. Next, zero pronouns within a Japanese sentence are identified by using the syntactic and semantic structure of the Japanese sentence and their antecedents within the English sentence are identified by using the characteristics of anaphoric and deictic expressions in English. This method was implemented using the Japanese-to-English machine translation system, ALT-3/E for the analysis of Japanese sentences and Brill's tagger for the analysis of the English sentences. According to my evaluation, for 554 zero p~onouns in a sentence set for the evaluation of 3apanese-to-Engllsh machine translation systems, 91.5% of the pairs of zero pronouns in the Japanese sentences and their antecedents in the English translations were automatically identified correctly. 1 ! n / ; r o d u c t i o n 1.1 M o t i v a t i o n In natural languages, elements that can be easily deduced by the reader are frequently omitted from expressions in texts (Kuno, 1978). This phenomenon causes considerable problems in natural language processing systems. For example, in a machine translation system, the system needs to recognize those elements which are not present in the source language, but may become mandatory elements in the target language. In particular, the subject and object are often omitted in Japanese; whereas they are normally obligatory in English. Thus, in Japanese-to-Engiish m a ~ n e translation systems, it is necessary to identify case elements omitted from the original Japanese ("zero pronouns") for their translation into Engiish expressions. Several algorithms have been proposed with regard to this problem (Kameyama, 1986; Walker et al., 1990; ¥oshimoto, 1988; Dousa~a, 1994). V/hen considering the application of these methods to a practical machine translation system for which the translation target area can not be 1/mired, it is not possible to apply them directly, both because their precision of resohtion is low as they only use limited information, and because the volume of knowledge that must be prepared beforehand is so large.