Method and device for automatically identifying statement relationship and entity

Abstract

The invention belongs to the technical field of intelligent identification and provides a method and a device for automatically identifying a statement relationship and an entity. The method for automatically identifying the statement relationship and the entity comprises the steps of projecting an input statement of a user to a fixed dimension space to obtain a sentence vector of the input statement in the fixed dimension space; inputting the sentence vector to a pretrained deep learning classifier to obtain a relationship category of the input statement; and identifying the entity in the input statement if the relationship category is identified. According to the method and the system provided by the invention, the input statement of the user is semantically judged by use of deep learning, and the relationship can be accurately identified; the entity identification is modeled as a sequence labeling problem, an optimal labeling is solved by use of a conditional random field and thus the entity is precisely identified; and the automation extraction of the relationship and the entity is realized in combination with the deep learning and the conditional random field.

Description

technical field [0001] The invention relates to the field of intelligent recognition technology, in particular to a method and device for automatically recognizing sentence relationships and entities. Background technique [0002] In the human-computer dialogue system, we often need to identify whether the user is expressing information in certain fields, such as preferences, nicknames, etc.; specific object. Usually, this information can be represented by relations and entities. The relationship mainly refers to what kind of information the user is expressing, such as whether it is a preference, a nickname, etc.; while the entity refers to the specific object referred to by the relationship. For example, if a user expresses "I like spicy hot pot", the corresponding relationship is "like", and the corresponding entity is "spicy hot pot". How to automatically recognize such domain-specific relations and entities in dialogue systems is a challenging problem. [0003] There...

AI Technical Summary

Problems solved by technology

[0010] 1. The problem of inaccurate relationship judgment

Only based on keywords or regular expressions, without considering the semantics of the sentence itself, which leads to misjudgment of relationships

[0011] 2. The problem of inaccurate entity extraction

Entities extracted based on regular expressions, SRL, syntax analysis, and dependency analysis are easily affected by the accuracy of the method itself, resulting in entity extraction errors

[0012] 3. With the increase of rules, the complexity of the system becomes higher, it is difficult to judge in advance whether the new rules are compatible with the original rules, so the system is difficult to maintain

Images