Graph Reasoning for Question Answering with Triplet Retrieval
This addresses the issue of limited knowledge retrieval in question answering for users of knowledge graphs, though it is incremental as it builds on existing retrieval and language model integration methods.
The paper tackled the problem of answering complex questions by reasoning over knowledge graphs, where existing methods constrain retrieved knowledge to local subgraphs, and proposed a method to retrieve and rerank relevant triplets, achieving up to 4.6% absolute accuracy improvement on CommonsenseQA and OpenbookQA datasets.
Answering complex questions often requires reasoning over knowledge graphs (KGs). State-of-the-art methods often utilize entities in questions to retrieve local subgraphs, which are then fed into KG encoder, e.g. graph neural networks (GNNs), to model their local structures and integrated into language models for question answering. However, this paradigm constrains retrieved knowledge in local subgraphs and discards more diverse triplets buried in KGs that are disconnected but useful for question answering. In this paper, we propose a simple yet effective method to first retrieve the most relevant triplets from KGs and then rerank them, which are then concatenated with questions to be fed into language models. Extensive results on both CommonsenseQA and OpenbookQA datasets show that our method can outperform state-of-the-art up to 4.6% absolute accuracy.