<journal article>
Generating Candidates for Rewriting Based on an Indicator of Complex Dependency and It's Application to a Writing Tool

Creator
Language
Publisher
Date
Source Title
Vol
Issue
First Page
Last Page
Publication Type
Access Rights
Rights
Related DOI
Related URI
Relation
Abstract 文章の推敲支援を行うツールは多数存在するが,その多くは推敲支援に役立つ情報を提示するのみである.それらの情報を用いれば推敲作業自体は楽になるが,文章をどのように書き換えるかは書き手自身が考える必要がある.我々の研究室では,本稿に先立って係り受け解析過程モデルを作成した.このモデルは係り受けの複雑さの指標を基に文の複雑さを判定し,係り受けの複雑な文を抽出することができる.しかしどのように書き換えれば...文の複雑さが滅るかについては何も提示しない.そこで,この指標が下がるように,構文情報のみを用いて文の書き換え候補を作成することを考えた.複雑さの指標が下がれば,その文は書き換える前よりも複雑さが減っているといえる.さらに,この書き換え候補による推敲支援方法について述べる.
Many writing tools for Japanese documents only notice a point of improving a sentence to a writer. He has to consider by himself how to rewrite a text. Our laboratory has proposed the model which imitates human dependency analysis for a Japanese sentence. The model can extract a complex sentence based on the indicator of complex dependency. It does not notices, however, anything about the method of decreasing the complexity of the sentence. In this paper, we describe a generating method of candidates for rewriting based on the indicator. We apply, furthermore, the method to a writing tool.
show more

Hide fulltext details.

pdf YokobayashiIPSJ04 pdf 313 KB 482  

Details

Record ID
Peer-Reviewed
Subject Terms
ISSN
Type
Created Date 2009.04.22
Modified Date 2020.11.02

People who viewed this item also viewed