意味表現に基づくテキスト生成方法、意味表現に基づくテキスト生成装置、電子機器、非一時的なコンピュータ読み取り可能な記憶媒体及びコンピュータプログラム

Japanese Patent JP7201654

B2

The present disclosure discloses a method and an apparatus for generating a text based on a semantic representation and relates to a field of natural language processing (NLP) technologies. The method for generating the text includes: obtaining (101) an input text, the input text comprising a source text; obtaining (102) a placeholder of an i^th word to be predicted in a target text; obtaining (103) a vector representation of the i^th word to be predicted, in which the vector representation of the i^th word to be predicted is obtained by calculating the placeholder of the i^th word to be predicted, the source text and 1^st to (i-1)^th predicted words by employing a self-attention mechanism; and generating (104) an i^th predicted word based on the vector representation of the i^th word to be predicted, to obtain a target text.

WO/2021/086589	PROVIDING A RESPONSE IN AUTOMATED CHATTING
JP7215038	Information processing device and information processing program
JP2022012457	INFORMATION PROCESSING DEVICE, INFORMATION PROCESSING SYSTEM, INFORMATION PROCESSING METHOD, AND PROGRAM

Chang, Han
Xiao, Dongling
Lee, Yukun
Sun, you
Tian, Hao
Wu, Fa
Wan, Haifen

JP2020208905A

January 10, 2023

December 17, 2020

Click for automatic bibliography generation  

Beijing Baidu Netcom Science Technology Co., Ltd.

G06F40/56; G06N20/00

ALLAMAR Jay,The Illustrated GPT-2 (Visualizing Transformer Language Models),米国,2019年08月12日,[2021年12月7日検索], インターネット
RADFORD Alec et al.,Improving Language Understanding by Generative Pre-Training,米国,2018年06月11日,pp.1-12,[2021年12月7日検索], インターネット
RADFORD Alec et al.,Language models are unsupervised multitask learners,米国,2019年02月14日, [2021年12月7日検索], インターネット
Kosuke-Szk,汎用言語表現モデルBERTを日本語で動かす(PyTorch),2019年05月01日,[2022年11月29日検索], インターネット

Kunio Ueda

Previous Patent: caulking stripper

Next Patent: MULTILAYER ELECTRONIC DEVICE