This paper outlines our approach to disambiguation in our Japanese-to-English system. First, it briefly shows the design concept of the Multi-Level Translation Method and discusses the necessity of semantic analysis in implementing this method. Second, it introduces our two approaches involving semantic analysis for disambiguation. Then it discusses semantic analysis and introduces the outline of our semantic dictionary prepared for semantic analysis, together with their e#ects on disambiguation. And finally, the paper outlines our plans to tackle problems which still remain. Keywords Japanese-to-English Machine Translation, Constructive Process Theory, Disambiguation, Linguistic Knowledge, Semantic Dictionaries 1

This paper describes a method of alignment between the noun part of WordNet and Goi-Taikeis Ontology. The result of the automatic alignment shows that matching words in Japanese as well as in English is highly efficient in extracting correct matches. Analyses of correct alignments by hand illustrate that, in ontology alignment, it is not always possible to preserve relative relations between concepts such as hyponymy or antonymy.

In this paper we show to what degree the countability of English nouns is predictable from their semantics. We found that at 78 % of nouns’ countability could be predicted using an ontology of 2,710 nodes. We also show how this predictability can be used to aid non-native speakers to determine the countability of English nouns when building a bilingual machine translation lexicon. 1

Potentially all Japanese nouns are under-specified with respect to number and countability. To ask a user to interactively disambiguate each one is not feasible, and it can be impossible for a native speaker to do. Therefore it is important to disambiguate automatically. In addition, even if the system makes a mistake about number, it is rarely fatal. There are some ambiguities involved with the use of classifiers that are more likely to be serious and require world knowledge such as 500-gm-no ringo which could mean either a 500gm apple or 500gm of apple(s). It may be appropriate to ask for user input to disambiguate such examples, although it may be preferable to query a knowledge base first. Keywords Automatic Disambiguation, Interactive Disambiguation, Classifiers, Countability, Japaneseto -English Machine Translation 1

We present a method for compositionally translating noun-noun (NN) compounds, using a word-level bilingual dictionary and syntactic templates for candidate generation, and corpus and dictionary statistics for selection. We propose a support vector learning-based method employing target language corpus and bilingual dictionary data, and evaluate it over a English   Japanese machine translation task. We show the proposed method to be superior to previous methods and also robust over low-frequency NN compounds.

In this paper, we outline the development of a system that automatically constructs ontologies by extracting knowledge from dictionary definition sentences using Robust Minimal Recursion Semantics (RMRS). Combining deep and shallow parsing resource through the common formalism of RMRS allows us to extract ontological relations in greater quantity and quality than possible with any of the methods independently. Using this method, we construct ontologies from two different Japanese lexicons and one English lexicon. We then link them to existing, handcrafted ontologies, aligning them at the word-sense level. This alignment provides a representative evaluation of the quality of the relations being extracted. We present the results of this ontology construction and discuss how our system was designed to handle multiple lexicons and languages. 1

Information on subcategorization and selectional restrictions is very important for natural language processing in tasks such as monolingual parsing, accurate rule-based machine translation and automatic summarization. However, adding this detailed information to a valency dictionary is both time consuming and costly.

Abstract. This paper describes in outline a method for translating Japanese temporal expressions into English. We argue that temporal expressions form a special subset of language that is best handled as a special module in machine translation. The paper deals with problems of lexical idiosyncrasy as well as the choice of articles and prepositions within temporal expressions. In addition temporal expressions are considered as parts of larger structures, and the question of whether to translate them as noun phrases or adverbials is addressed. 1

This paper proposes a powerful method for the resolution of Japanese zero pronouns in a text with meta information which indicates the textual structure. This method uses not only semantic and pragmatic constraints but also information about the text structure. According to a window test for 480 zero pronouns in a specification with explicit structural information, all of the zero pronouns could be resolved consistently and correctly. Furthermore, 93% of zero pronouns with intersentential antecedents could be resolved correctly using only structural information in the text. This result indicates that, for a text with explicit structural information, the information can be used to e#ectively resolve zero pronouns with intersentential antecedents. 1 Introduction In all natural languages, elements that can be easily deduced by the reader are frequently omitted from expressions in texts (Kuno 1978). This phenomenon causes big problems in any natural language processing system. Fo...

We present a method for combining two bilingual lexicons to make a third, using one language as a pivot. In this case we combine a Japanese-English lexicon with a Malay-English lexicon, to produce a Japanese-Malay lexicon suitable for use in a machine translation system. Our method di#ers from previous methods in its use of semantic classes to rank translation equivalents: word pairs with compatible semantic classes are preferred to those with dissimilar classes. We have made a prototype lexicon of over 75,000 pairs, and are now in the process of removing inappropriate entries by hand. 1