US 11,861,305 B2
Word processing system and word processing method
Yudai Kato, Tokyo (JP); Noriko Takaya, Tokyo (JP); Takahiro Hamada, Tokyo (JP); and Junya Sawazaki, Tokyo (JP)
Assigned to HITACHI, LTD., Tokyo (JP)
Appl. No. 17/599,041
Filed by HITACHI, LTD., Tokyo (JP)
PCT Filed Dec. 7, 2020, PCT No. PCT/JP2020/045521
§ 371(c)(1), (2) Date Sep. 28, 2021,
PCT Pub. No. WO2022/123637, PCT Pub. Date Jun. 16, 2022.
Prior Publication US 2022/0350964 A1, Nov. 3, 2022
Int. Cl. G06F 40/211 (2020.01); G06F 40/40 (2020.01)
CPC G06F 40/211 (2020.01) [G06F 40/40 (2020.01)] 7 Claims
OG exemplary drawing
 
1. A word processing system, comprising:
a first generation unit which generates, based on sentence information including a plurality of sentences, hierarchy data indicating a syntax tree for each hierarchy with regard to each sentence;
a second generation unit which
acquires, from a plurality of hierarchy data generated by the first generation unit, hierarchy data of a second sentence similar to hierarchy data of a first sentence generated by the first generation unit,
extracts a difference between the hierarchy data of the first sentence and the hierarchy data of the second sentence, and
generates, as paraphrasing rule data, first expression data as a difference in the first sentence and second expression data as a difference in the second sentence; and
a storage unit which stores the paraphrasing rule data generated by the second generation unit in a storage unit,
wherein the plurality of sentences including the first sentence and the second sentence are in a same natural language,
wherein the first sentence and the second sentence are similar as paraphrases and are not identical,
wherein the first expression data consists of nodes in a syntax tree of the second sentence that are not present in a syntax tree of the first sentence,
wherein the second expression data consists of nodes in the syntax tree of the first sentence that are not present in the syntax tree of the second sentence, and
wherein the paraphrasing rule data converts the first expression data into the second expression data.