IP Library Granted Patent US 12,632,672
Granted Patent B2
US 12,632,672 · App. 18/280,181 · Granted May 19, 2026

Learning apparatus, learning method and program

Inventors: Kosuke Nishida (Tokyo, JP); Kyosuke Nishida (Tokyo, JP); Sen Yoshida (Tokyo, JP)
Assignee: NTT, Inc.
G06F40/40G06N3/0455
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,632,672
App. No.
18/280,181
Granted
May 19, 2026
Kind
B2
Abstract

A learning apparatus includes a memory and at least one processor connected to the memory, wherein the processor configured to: convert input text data into a feature amount sequence based on a language model; and update parameters of the language model based on the text data, the feature amount sequence, and a word vector learned in advance.

Claims (32)

1 . A learning apparatus comprising:

a memory; and

at least one processor connected to the memory,

wherein the processor configured to:

convert input text data into a feature amount sequence of the input text data based on a language model, wherein the language model is pre-trained in a first subject domain; and

update, as training of the language model, parameters of the language model based on the text data, the feature amount sequence of the input text data, and a word vector,

wherein the word vector is learned in advance in a second subject domain, the second subject domain is a part of the first subject domain, the word vector represents semantics of a word in the second subject domain, thereby the language model with the updated parameters as trained performing a target task of the second subject domain with accuracy, and

in a case where the word vector includes word vectors of subwords obtained by dividing a word, and the language model divides the text data to have a finer granularity than a word, update the parameters of the language model based on the word vectors of the subwords.

2 . A learning apparatus comprising:

a memory; and

at least one processor connected to the memory,

wherein the processor configured to:

convert input text data into a feature amount sequence of the input text data based on a language model, wherein the language model is pre-trained in a first subject domain; and

update, as training of the language model, parameters of the language model based on the text data, the feature amount sequence of the input text data, and a word vector,

wherein the word vector is learned in advance in a second subject domain, the second subject domain is a part of the first subject domain, the word vector represents semantics of a word in the second subject domain, thereby the language model with the updated parameters as trained performing a target task of the second subject domain with accuracy, and

in a case where the language model divides the text data to have a finer granularity than a word, update the parameters of the language model based on an average value of intermediate representations of the language model and the word vector for subwords belonging to a same word.

3 . A learning method to be executed by a computer including a memory and at least one processor connected to the memory, the method comprising:

converting input text data into a feature amount sequence of the input text data based on a language model, wherein the language model is pre-trained in a first subject domain; and

updating, as training of the language model, parameters of the language model based on the text data, the feature amount sequence of the input text data, and a word vector,

wherein the word vector is learned in advance in a second subject domain, the second subject domain is a part of the first subject domain, the word vector represents semantics of a word in the second subject domain, thereby the language model with the updated parameters as trained performing a target task of the second subject domain with accuracy, and

in a case where the word vector includes word vectors of subwords obtained by dividing a word, and the language model divides the text data to have a finer granularity than a word, update the parameters of the language model based on the word vectors of the subwords.

4 . A non-transitory computer-readable recording medium having computer-readable instructions stored thereon, which, when executed, cause a computer to function as the learning apparatus according to claim 1 .

5 . The learning apparatus according to claim 1 ,

wherein the word is at least a part of the input text data.

6 . The learning apparatus according to claim 1 ,

wherein the word vector is learned in advance by using another corpus,

said another corpus comprises more text data than the corpus, thereby the word vector capturing a knowledge that the pre-trained language model lacks.

7 . The learning apparatus according to claim 1 ,

wherein the word vector is learned in advance based on a general corpus, and

an amount of the corpus is greater than a total amount of the input text data.

8 . The learning apparatus according to claim 1 ,

wherein a domain of the input text data is the same as a domain of text data to be processed in a target task.

Assignments (2)
CHANGE OF NAME Recorded Oct 22, 2025
From: NIPPON TELEGRAPH AND TELEPHONE CORPORATION
To: NTT, INC.
Reel/Frame 073184/0647 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Sep 1, 2023
From: NISHIDA, KOSUKE; NISHIDA, KYOSUKE; YOSHIDA, SEN
To: NIPPON TELEGRAPH AND TELEPHONE CORPORATION
Reel/Frame 064780/0596 →
Continuity (1)
Related Publication 20240054295A1 · Feb 15, 2024
References Cited (11)
US 10699060B2 · McCann · 2020 [cited by examiner]
US 20230244879A1 · Zhang · 2023 [cited by examiner]
CN 111914551A · 2020 [cited by examiner]
CN 113536800A · 2021 [cited by examiner]
Gururangan et al. (2020) “Don't stop pretraining: Adapt language models to domains and tasks,” In ACL, pp. 8342-8360, Jul. 2020. [cited by applicant]
Devlin et al. (2019) “BERT: Pre-training of deep bidirectional transformers for language understanding,” NAACL-HLT, pp. 4171-4186. [cited by applicant]
Lee et al. (2020) “Biobert: a pre-trained biomedical language representation model for biomedical text mining,” Bioinformatics, vol. 36, No. 4, pp. 1234-1240. [cited by applicant]
Mikolov et al. (2013) “Efficient Estimation of Word Representations,” in Vector Space, pp. 1-12. [cited by applicant]
Bojanowski et al. (2017) “Enriching word vectors with subword information,” Transactions of the Association for Computational Linguistics, vol. 5, pp. 135-146. [cited by applicant]
Tsatsaronis et al. (2015) “An overview of the BIOASQ large-scale biomedical semantic indexing and question answering competition,” BMCBioinformatics, vol. 16, p. 138. [cited by applicant]
Rajpurkar et al. (2016) “SQuAD: 100,000+ questions for machine comprehension of text,” In EMNLP, pp. 2383-2392. [cited by applicant]