Seiji Miike

Abstract generation based on rhetorical structure extraction

We have developed an automatic abstract generation system for Japanese expository writings based on rhetorical structure extraction. The system first extracts the rhetorical structure, the compound of the rhetorical relations between sentences, and then cuts out less important parts in the extracted structure to generate an abstract of the desired length.Evaluation of the generated abstract showed that it contains at maximum 74% of the most important sentences of the original text. The system is now utilized as a text browser for a prototypical interactive document retrieval system.

A full-text retrieval system with a dynamic abstract generation function

We have developed a Japanese full-text retrieval system named BREVIDOC* that enables the user to specify an area within a text for abstraction and to control the volume of the abstract interactively. This system analyzes a document structure using linguistic knowledge only and thus is domain-independent. In its text structure analysis, the system determines relations among paragraphs and sentences, based on linguistic clues such as connectives, anaphoric expressions, and idiomatic expressions. The system analyzes and stores the text structure in advance so that it can generate an abstract in real time by selecting sentences according to relative importance of rhetorical relations among the sentences. The retrieval system works on an engineering workstation.

Document structure extraction for interactive document retrieval systems

0.92 0.71 0.29 0.64 (A) (B) (c) original 0.28 0.50 0.43 0.40 I I (c) I (A) I (B) I

Automatic abstract generation based on document structure analysis and its evaluation as a document retrieval presentation function

An automatic abstract generation system including a document structure analyzer is described. From a document, the system extracts a text structure representing rhetorical relations among sentences and sentence chunks. The system evaluates sentence importance based on the analyzed structure and decides which sentence should be discarded from an abstract. It also attempts to generate an abstract consistent with the original text by replacing connective expressions. Generated abstracts were evaluated from two points of view: the cover rate of key sentences; and the quality as document presentation media. Both experimental results proved the generated abstracts to be valid.

EXPERIENCES WITH AN ON-LINE TRANSLATING DIALOGUE SYSTEM

An English-Japanese bi-directional machine translation system was connected to a keyboard conversation function on a workstation, and tested via a satellite link with users in Japan and Switzerland. The set-up is described, and some informal observations on the nature of the bilingual dialogues reported.

The treatment of complex English nominalizations in machine translation

This paper concerns the treatment, in the context of machine translation, of English complex nominal groups which can be considered as nominalizations of verb phrases. We discuss the fact that many styles of English prose which are suitable for translation by machine typically favor the use of nominal rather than verbal syntagms. But such constructions when translated literally are often considered unnatural. The general problem is described in detail, with examples. The more specific problem of recognizing nominalizations and analyzing their structure is considered. How and where to achieve the required syntactic ‘transformation’ is discussed, and exemplified.

Information filtering system operated for NewsWatch’s Daily News Filtering Service

情報通信技術やインフラの向上により日々生成され取得できる情報が増大している中で，情報検索だけではなく必要な情報のみを抽出して提示する情報フィルタリングの必要性が高まっている。株式会社ニューズウォッチは，1996年から新聞を中心とした100を越える媒体からユーザの要求に応じた記事を抽出しユーザに提示する情報フィルタリングサービスを提供している。本記事では，ニューズウォッチ社の各種サービスを支える，自然言語処理技術とWeb技術を用いた情報フィルタリングシステムおよびサービス提供システムについて解説する。