Anaphora resolution model training method and apparatus, and electronic device

Abstract

The embodiment of the invention provides an anaphora resolution model training method and device and electronic equipment. The method comprises the steps: screening corpora meeting a target condition from a preset corpus pool, wherein the corpus meeting the target condition at least comprises a first candidate noun, a second candidate noun and a target noun, the first candidate noun is the same as the target noun, and the second candidate noun is different from the target noun; replacing the target noun in the corpus meeting the target condition with a preset identifier, replacing the first candidate noun with a first preset noun, and replacing the second candidate noun with a second preset noun to obtain target corpora; and generating annotation information corresponding to the target corpora, and training according to the target corpora and the annotation information corresponding to the target corpora. According to the embodiment of the invention, a large number of target corpora used for training the anaphora resolution model are constructed in an automatic manner, so that the process of manually annotating the corpora is avoided, and the whole process of training the anaphora resolution model is time-saving and labor-saving.

Description

technical field [0001] The invention relates to the field of natural language processing, in particular to a training method, device and electronic equipment for an anaphora resolution model. Background technique [0002] In the field of natural language processing, machines are required to perform semantic analysis and semantic understanding of natural language, so as to predict the nouns referred to by pronouns in natural language. Among them, the process of determining the nouns referred to by pronouns can be understood as anaphora resolution. It can also be simply understood that anaphora resolution refers to predicting the nouns referred to by the pronouns in the sentence. [0003] Usually, in order to ensure the prediction accuracy of the anaphora resolution model, it is necessary to use a large amount of corpus with annotation information to train it. Among them, the annotation information is the nouns correctly referred to by the pronouns and the nouns referred to ...

AI Technical Summary

Problems solved by technology

[0005] In view of the above problems, embodiments of the present invention provide a training method and device for anaphora resolution models, and electronic equipment to solve the problem of time-consuming and laborious training of anaphora resolution models in the prior art.

Images