Toru Hitaka

An attempt to automatic thesaurus construction from an ordinary Japanese language dictionary

How to obtain hierarchical relations (e.g. superordinate-hyponym relation, synonym relation) is one of the most important problems for thesaurus construction. A pilot system for extracting these relations automatically from an ordinary Japanese language dictionary (Shinmeikai Kokugojiten, published by Sansei-do, in machine readable form) is given. The features of the definition sentences in the dictionary, the mechanical extraction of the hierarchical relations and the estimation of the results are discussed.

A syntax parser based on the case dependency grammar and its efficiency

Augumented transition network grammars (ATNGs) or augumented contextfree grammars are generally used in natural language processing systems. The advantages of ATNGs may be summarized as i) efficiency of representation, 2) perspicuity, 3) generative power, and the disadvantage of ATNGs is that it is difficult to get an efficient parsing algorithm becuase of the flexibility of their complicated additional functions. In this paper, the syntax of Japanese sentences , based on case dependency relations are stated first, and then we give an bottom-up and breadth-first parsing algoritbxnwhich parses input sentence using time O(n 3) and memory space O(n2), where n is the length of input sentence. Moreover, it is shown that this parser requires time O(n2), whenever each B-phrase in input sentence is unambiguous in its grammatical structure. Therefore, the efficiency of this parser is nearly equal to the Earleys parser which is the most efficient parsing method for general context-free grammars.

A Method of Automatic Summarization to Maximize the Flow of Subjects in a Summary

重要文抽出法に基づく要約手法に対する研究に一応の成熟が見られる中で, informativeな要約の実現へ向けて要約文の可読性の問題が取り上げられてきている.そこで本研究では, 話題の連想による文間, 段落問の繋がりに着目し, 要約文中の話題の流れの合計を最大にすることによって, 読みやすい要約文を得ることを試みる.要約システムはまず, 文章中で話題の流れが途切れる個所で段落分けし, 階層的な段落構造を構築する.次に, 話題の流れの解析によって導入部, 結論部を検出し保存する.そして, 周囲の話題の流れへの寄与率を評価値として閾値未満の不要な部分を選択し, 段落単位で削除していくことによって要約文を作成する.またその際, 自動的に閾値を補正し再試行することによって, 要約率の誤差をできるだけ小さく抑える.以上により, 文と文, 段落と段落が話題の連想による結束性で強く結び付いた, 読みやすい要約文を得ることができる.新聞の社説記事を用いた評価実験により, 提案手法は, まだ人手による要約と比べるとやや物足りないが, 比較的読みやすい要約文を生成することがわかった.また, 要約率30%の要約文中に原文中の結論が保存される割合は77.5%であった.

Estimating satisfactoriness of selectional restriction from corpus without a thesaurus

A selectional restriction specifies what combinations of words are semantically valid in a particular syntactic construction. This is one of the basic and important pieces of knowledge in natural language processing and has been used for syntactic and word sense disambiguation. In the case of acquiring the selectional restriction for many combinations of words from a corpus, it is necessary to estimate whether or not a word combination that is not observed in the corpus satisfies the selectional restriction. This paper proposes a new method for estimating the degree of satisfaction of the selectional restriction for a word combination from a tagged corpus, based on the multiple regression model. The independent variables of this model correspond to modifiers. Unlike a conventional multiple regression analysis, the independent variables are also parameters to be learned. We experiment on estimating the degree of satisfaction of the selectional restriction for Japanese word combinations ⟨noun, postpositional-particle, verb⟩. The experimental results indicate that our method estimates the degree of satisfaction of a word combination not very well observed in the corpus, and that the accuracy of syntactic disambiguation using the co-occurrencies estimated by our method is higher than using co-occurrence probabilities smoothed by previous methods.

Logical form of hierarchical relation on verbs and extracting it from definition sentences in a Japanese dictionary

We are studying how to extract hierachical relation on verbs from definition sentences in a Japanese dictionary. The hierarchical relation on verbs has been dealt with as a binary relation on verbs, but it should be dealt with as logical relation on predicates. We will define the logical form of the hierarchical relation on verbs and then discuss which part of the syntactic structure of the definition sentence represents that relation. We will call the main predicate verb in this part the definition verb. Furthermore we will describe how to semiautomatically select the proper meaning of the definition verb and the proper correspondence between cases of an entry verb and the definition verb in order to extract the hierarchical relation as logical relation.