DOMAIN KNOWLEDGE UTILIZATION SUPPORT DEVICE, PROGRAM, AND DOMAIN KNOWLEDGE UTILIZATION SUPPORT METHOD
To enable extraction of features about a domain included in a text.SOLUTION: A domain knowledge utilization support device 100 includes: a text division part 111 dividing a text into sentences; a domain determination part 112 determining a domain related to sentences; an implication extraction part...
Gespeichert in:
Hauptverfasser: | , , |
---|---|
Format: | Patent |
Sprache: | eng ; jpn |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | To enable extraction of features about a domain included in a text.SOLUTION: A domain knowledge utilization support device 100 includes: a text division part 111 dividing a text into sentences; a domain determination part 112 determining a domain related to sentences; an implication extraction part 113 which refers to an implication information database 130 that stores a word in association with its implication and extracts implications of the sentence; a domain information extraction part 114 which refers to a domain specific category information database 140 storing a word in association with a category of the word every domain, and extracts the word and the category of the word from the sentence; and a structuring part 116 which converts the text into a tree including a node corresponding to the implication of the sentence and a node corresponding to the category.SELECTED DRAWING: Figure 1
【課題】テキストに含まれるドメインに係る特徴の抽出を可能とする。【解決手段】ドメイン知識活用支援装置100は、テキストを文に分割するテキスト分割部111、文が係るドメインを判定するドメイン判定部112、語と当該語の含意とを関連付けて記憶する含意情報データベース130を参照して、文の含意を抽出する含意抽出部113、ドメイン別に語と当該語のカテゴリとを関連付けて記憶するドメイン別カテゴリ情報データベース140を参照して、文から語と当該語のカテゴリとを抽出するドメイン情報抽出部114、およびテキストを文の含意に対応するノードとカテゴリに対応するノードとを含む木に変換する構造化部116を備える。【選択図】図1 |
---|