Correction of Faulty Background Knowledge based on Condition Aware and Revise Transformer for Question Answering
This addresses a practical issue in e-commerce customer service by handling defective condition values, though it is incremental as it builds on existing Transformer-based QA systems.
The paper tackles the problem of question answering when external condition information is faulty or incomplete, proposing CAR-Transformer to revise conditions and select answers, resulting in substantial outperformance over baselines on a real-world dataset.
The study of question answering has received increasing attention in recent years. This work focuses on providing an answer that compatible with both user intent and conditioning information corresponding to the question, such as delivery status and stock information in e-commerce. However, these conditions may be wrong or incomplete in real-world applications. Although existing question answering systems have considered the external information, such as categorical attributes and triples in knowledge base, they all assume that the external information is correct and complete. To alleviate the effect of defective condition values, this paper proposes condition aware and revise Transformer (CAR-Transformer). CAR-Transformer (1) revises each condition value based on the whole conversation and original conditions values, and (2) it encodes the revised conditions and utilizes the conditions embedding to select an answer. Experimental results on a real-world customer service dataset demonstrate that the CAR-Transformer can still select an appropriate reply when conditions corresponding to the question exist wrong or missing values, and substantially outperforms baseline models on automatic and human evaluations. The proposed CAR-Transformer can be extended to other NLP tasks which need to consider conditioning information.