Method and device for providing multi-granularity word segmentation result

The invention discloses a method and device for providing a multi-granularity word segmentation result, which are used for avoiding the problem of semanteme term loss or lower word segmentation accuracy when providing the multi-granularity word segmentation result. The method comprises the following...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: CHU MIN, PENG RENGANG, YANG YANG, SUN JIAN, TANG JINGMING, XU BINGJING, LIAO XIAOLING, HOU LEI
Format: Patent
Sprache:chi ; eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:The invention discloses a method and device for providing a multi-granularity word segmentation result, which are used for avoiding the problem of semanteme term loss or lower word segmentation accuracy when providing the multi-granularity word segmentation result. The method comprises the following steps of: establishing a minimal semantic unit dictionary; carrying out word segmentation treatment on a given text according to the minimal semantic unit dictionary to obtain an intermediate-granularity word segmentation result; merging the intermediate-granularity word segmentation result according to a dictionary with the granularity being larger than that of the minimal semantic unit dictionary to obtain a first-granularity word segmentation result with the granularity being larger than that of the intermediate-granularity word segmentation result; and searching a retrieval unit contained in a segmentation unit in the minimal semantic unit dictionary by sequentially aiming at each segmentation unit in the inte