A method for resolution of anaphora in a multi-turn dialogue system

Abstract

A method for referring to a multi-round dialogue system provided by the present invention includes the following steps: S1. Detecting sentences received by a multi-round dialogue system, and judging whether a sentence needs to be referred to and clearing up, and if so, proceed to step In S2; S2. Judging the sentence that needs to be resolved for reference, distinguishing the reference type of the sentence, and screening out candidate entities from the sentences that distinguish the reference type; the reference type of the sentence includes an anaphora sentence and Co-reference sentence; S3. Determine the distance between the candidate entity and the pronoun in the sentence, and use the candidate entity with the smallest distance as the reference link word; S4. Update the reference pronoun to the reference link word; through the above method, multiple rounds of input can be Accurate recognition of the reference of sentences in the dialogue system and accurate resolution of reference can effectively improve the smoothness of the multi-round interactive system and enhance the user experience.

Description

technical field [0001] The invention relates to the field of man-machine dialog language processing, in particular to a method for resolution of anaphora in a multi-round dialog system. Background technique [0002] Reference is a common linguistic phenomenon. In multi-turn dialogue systems, reference and omission affect the fluency and user experience of human-computer dialogue systems. The human brain has a knowledge background and memory ability, and can reproduce the key information of the dialogue history very well, and automatically complete or replace the pronouns of the other party's current turn to understand the true meaning of the dialogue. Similarly, a reference resolution module is needed in a human-computer dialogue system to understand the real semantics of user input. [0003] The anaphora resolution methods are divided into pipeline-based methods and end-to-end based methods. Pipeline-based approaches perform coreference detection first, followed by coref...

AI Technical Summary

Problems solved by technology

End-to-end methods usually use deep learning models, but require a large amount of labeled data, and the cost of model construction is relatively high in the face of lack of domain data, especially in the early stages of multi-round referral resolution. Encountered problems in the process, the model modification iteration does not meet the timeliness of the online system

Images