Multi-Instance Learning for End-to-End Knowledge Base Question Answering
This work addresses noisy answer handling in KBQA for real-world applications, representing an incremental improvement over existing methods.
The paper tackled the problem of noisy answers in end-to-end knowledge base question answering by proposing a multiple instance learning approach that explores consensus among answers, resulting in significant improvements in entity accuracy and Rouge-L score on the CQA dataset.
End-to-end training has been a popular approach for knowledge base question answering (KBQA). However, real world applications often contain answers of varied quality for users' questions. It is not appropriate to treat all available answers of a user question equally. This paper proposes a novel approach based on multiple instance learning to address the problem of noisy answers by exploring consensus among answers to the same question in training end-to-end KBQA models. In particular, the QA pairs are organized into bags with dynamic instance selection and different options of instance weighting. Curriculum learning is utilized to select instance bags during training. On the public CQA dataset, the new method significantly improves both entity accuracy and the Rouge-L score over a state-of-the-art end-to-end KBQA baseline.