US 11,669,690 B2
Method and apparatus for processing sematic description of text entity, and storage medium
Songtai Dai, Beijing (CN); Xinwei Feng, Beijing (CN); Miao Yu, Beijing (CN); Huanyu Zhou, Beijing (CN); Xunchao Song, Beijing (CN); and Pengcheng Yuan, Beijing (CN)
Assigned to BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY CO., LTD., Beijing (CN)
Filed by BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY CO., LTD., Beijing (CN)
Filed on Jan. 14, 2021, as Appl. No. 17/149,226.
Claims priority of application No. 202010041592.7 (CN), filed on Jan. 15, 2020.
Prior Publication US 2021/0216722 A1, Jul. 15, 2021
Int. Cl. G06F 17/00 (2019.01); G06F 40/30 (2020.01); G06F 16/35 (2019.01); G06F 40/295 (2020.01)
CPC G06F 40/30 (2020.01) [G06F 16/35 (2019.01); G06F 40/295 (2020.01)] 9 Claims
OG exemplary drawing
 
1. A method for processing a sematic description of a text entity, comprising:
acquiring a plurality of target texts containing a main entity, and extracting related entities describing the main entity from each target text;
acquiring a sub-relation vector of a pair of the main entity and each related entity in each target text;
calculating a similarity distance of the main entity between different target texts based on the sub-relation vector; and
determining a semantic similarity of the main entity descripted in different target texts based on the similarity distance,
wherein the acquiring the sub-relation vector of the pair of the main entity and each related entity in each target text comprises:
acquiring a first vector representation of each word in the target text;
weighting the first vector representation, the main entity, and each related entity based on a pre-trained conversion model, and acquiring a second vector representation of a text content associated with the main entity and each related entity in the target text; and
performing a pooling process on the second vector representation to generate the sub-relation vector of the pair of the main entity and each related entity.