公开(公告)号：US20210390454A1

公开(公告)日：2021-12-16

申请号：US17343955

申请日：2021-06-10

申请人： Tianxiong XIAO ,  Yixuan TONG ,  Bin DONG ,  Shanshan JIANG ,  Jiashi ZHANG

发明人： Tianxiong XIAO ,  Yixuan TONG ,  Bin DONG ,  Shanshan JIANG ,  Jiashi ZHANG

IPC分类号： G06N20/00 ,  G06F40/20 ,  G06K9/62

摘要： Disclosed is an apparatus for training a machine reading comprehension model. The apparatus is inclusive of a distance calculation part configured to calculate, based on a position of each word within a training text and a position of an answer label within the training text, a distance between the same word and the answer label; a label smoothing part configured to input the distance between the same word and the answer label into a smooth function to obtain a probability value corresponding to the same word, outputted from the smooth function; and a model training part configured to make the probability value corresponding to the same word serve as a smoothed label of the same word so as to train the machine reading comprehension model.

公开(公告)号：US20230073746A1

公开(公告)日：2023-03-09

申请号：US17821227

申请日：2022-08-22

申请人： Tianxiong XIAO ,  Rui CHENG ,  Bin DONG ,  Shanshan JIANG ,  Jiashi ZHANG

发明人： Tianxiong XIAO ,  Rui CHENG ,  Bin DONG ,  Shanshan JIANG ,  Jiashi ZHANG

IPC分类号： G06F40/47 ,  G06F40/30 ,  G06F40/205

摘要： A method and an apparatus for machine reading comprehension, and a non-transitory computer-readable recording medium are provided. In the method, a paragraph-question pair is obtained, and subword vectors corresponding to subwords in the paragraph-question pair are generated. Then, for each subword, relative positions of the subword with respect to the other subwords are determined based on distances, and self-attention information of the subword in a first part and mutual attention information of the subword in a second part are calculated by using the relative positions and the subword vector. Then, a fusion vector of the subword is generated based on the self-attention information and the mutual attention information. Then, the fusion vectors of the subwords are input to a decoder of a machine reading comprehension model so as to obtain an answer predicted by the decoder.