公开(公告)号：US20200125673A1

公开(公告)日：2020-04-23

申请号：US16167552

申请日：2018-10-23

申请人： International Business Machines Corporation

发明人： RANIT AHARONOV ,  Liat Ein Dor ,  Alon Halfon ,  Yosi Mass ,  IIya Shnayderman ,  Noam Slonim ,  ELAD VENEZIAN

IPC分类号： G06F17/30 ,  G06F17/27 ,  G06K9/62 ,  G06N3/08 ,  G06N3/04

摘要： A method of estimating a thematic similarity of sentences, comprising receiving a corpus of a plurality of documents describing a plurality of topics where each document comprises a plurality of sentences arranged in a plurality of sections, constructing sentence triplets for at least some of the sentences, each sentence triplet comprising a respective sentence, a respective positive sentence selected randomly from the section comprising the respective sentence and a respective negative sentence selected randomly from another section, training a first neural network with the sentence triplets to identify sentence-sentence vectors mapping each sentence with a shorter distance to its respective positive sentence compared to the distance to its respective negative sentence and outputting the first neural network for estimating thematic similarity between a pair of sentences by computing a distance between the sentence-sentence vectors produced for each sentence of the pair by the first neural network.