US 11,934,782 B2
Neural reasoning path retrieval for multi-hop text comprehension
Julien Perez, Grenoble (FR); and Arnaud Sors, Grenoble (FR)
Assigned to NAVER CORPORATION, Gyeonggi-Do (KR)
Filed by NAVER CORPORATION, Gyeonggi-do (KR)
Filed on Oct. 21, 2021, as Appl. No. 17/506,917.
Claims priority of application No. 21305037 (EP), filed on Jan. 14, 2021.
Prior Publication US 2022/0222436 A1, Jul. 14, 2022
Int. Cl. G06F 40/284 (2020.01); G06F 16/93 (2019.01); G06N 3/04 (2023.01)
CPC G06F 40/284 (2020.01) [G06N 3/04 (2013.01); G06F 16/93 (2019.01)] 22 Claims
OG exemplary drawing
 
1. A question answering system comprising:
a neural network tokenizer module configured to determine a token representation of a question to be answered and token representations of candidate paragraphs of a present reasoning path for the question, respectively;
a neural network module configured to:
transform the token representation of the question and the token representations of the candidate paragraphs of the present reasoning path into vector representations; and
append a first variable to the vector representations to produce a second variable;
a search module configured to:
select the candidate paragraphs from a knowledge database to extend a present reasoning path based on lexical relevance of the candidate paragraphs to the question; and
selectively add ones of the candidate paragraphs to the present reasoning path,
wherein the neural network module is further configured to determine a score for the present reasoning path based on the second variable; and
an answer inference network module configured to selectively determine an answer to the question based on multiple different portions of the present reasoning path when the score of the present reasoning path is greater than a predetermined value.