Universal dependencies (UD) is a framework for morphosyntactic annotation of human language, which to date has been used to create treebanks for more than 100 languages. In this article, we outline the linguistic theory of the UD framework, which draws on a long tradition of typologically oriented grammatical theories. Grammatical relations between words are centrally used to explain how predicate–argument structures are encoded morphosyntactically in different languages while morphological features and part-of-speech classes give the properties of words. We argue that this theory is a good basis for cross-linguistically consistent annotation of typologically diverse languages in a way that supports computational natural language understanding as well as broader linguistic studies.

This paper describes a method of inducing wide-coverage CCG resources for Japanese. While deep parsers with corpusinduced grammars have been emerging for some languages, those for Japanese have not been widely studied, mainly because most Japanese syntactic resources are dependency-based. Our method first integrates multiple dependency-based corpora into phrase structure trees and then converts the trees into CCG derivations. The method is empirically evaluated in terms of the coverage of the obtained lexicon and the accuracy of parsing.

This paper compares domain-oriented and linguistically-oriented semantics, based on the GENIA event corpus and FrameNet. While the domain-oriented semantic structures are direct targets of Text Mining (TM), their extraction from text is not straghtforward due to the diversity of linguistic expressions. The extraction of linguistically-oriented semactics is more straghtforward, and has been studied independentely of specific domains. In order to find a use of the domain-independent research achievements for TM, we aim at linking classes of the two types of semantics. The classes were connected by analyzing linguistically-oriented semantics of the expressions that mention one biological class. With the obtained relationship between the classes, we discuss a link between TM and linguistically-oriented semantics.

This paper presents shallow semantic parsing based only on HPSG parses. An HPSG-FrameNet map was constructed from a semantically annotated corpus, and semantic parsing was performed by mapping HPSG dependencies to FrameNet relations. The semantic parsing was evaluated in a Senseval-3 task; the results suggested that there is a high contribution of syntactic information to semantic analysis.

Wide-coverage resources for lexicalized grammars have been obtained by converting the existing treebanks into collections of derivations. Additional annotations to the source treebank can be used to improve these derivations. A treebank annotation called the NTT treebank was used for this paper to improve a CCGbank for Japanese. The source treebank of the CCGbank itself is created by automatically converting chunk-dependencies, but the CCGbank contains errors caused by noisier phrase structures and a lack of linguistic information, which is difficult to represent in chunk-dependency. The NTT treebank provides cleaner trees and functional and semantic information, e.g., coordinations and predicate-argument structures. The effect of the improvement process is empirically evaluated in terms of the changes in the dependency relations extracted from the resulting derivations.