Method, device, and program for text classification
AssigneeFujitsu Limited
InventorsJumma Kudo, Daiki Hanawa, Toshihide Miyagi, Kota Yamakoshi, Keisuke Hirota
Life of this patent
Estimating the term…
Abstract
A text classification method is performed in a computer. The method includes: receiving a plurality of texts. When detecting that a text among the received plurality of texts includes a pause part satisfying a specific condition, dividing the text at the pause part and generating a new plurality of texts. The method may also include classifying texts, among the received plurality of texts, not including the pause part satisfying the specific condition, and the generated new plurality of texts into a plurality of clusters.
Claims18
A text classification method performed in a computer, the method comprising:
- receiving a plurality of texts;
- when detecting that a text among the received plurality of texts includes a pause part satisfying a specific condition, dividing the text at the pause part and generating a new plurality of texts;
- and
- classifying texts, among the received plurality of texts not including the pause part satisfying the specific condition and the generated new plurality of texts, into a plurality of clusters,
- when an appearance state in the plurality of texts of one of a former half portion and a latter half portion obtained by dividing the text at a pause part satisfies a predetermined condition, the pause part is set as the pause part satisfying the specific condition.
A text classification device comprising:
- a memory, and
- a processor coupled to the memory and configured to:
- receive a plurality of texts;
- divide, when detecting that a text among the received plurality of texts includes a pause part satisfying a specific condition, the text at the pause part and generating a new plurality of texts;
- and
- classify texts, among the received plurality of texts not including the pause part satisfying the specific condition and the generated new plurality of texts, into a plurality of clusters,
- when an appearance state in the plurality of texts of one of a former half portion and a latter half portion obtained by dividing the text at a pause part satisfies a predetermined condition, the pause part is set as the pause part satisfying the specific condition.
A non-transitory computer-readable storage medium storing a text classification program that causes a computer to perform a process comprising:
- receiving a plurality of texts;
- dividing, when detecting that a text among the received plurality of texts includes a pause part satisfying a specific condition, the text at the pause part and generating a new plurality of texts;
- and
- classifying texts, among the received plurality of texts not including the pause part satisfying the specific condition and the generated new plurality of texts, into a plurality of clusters,
- when an appearance state in the plurality of texts of one of a former half portion and a latter half portion obtained by dividing the text at a pause part satisfies a predetermined condition, the pause part is set as the pause part satisfying the specific condition.
Dependencies are inferred from the claim text.