TIARA: Multi-grained Retrieval for Robust Question Answering over Large Knowledge Bases
This addresses the challenge of robust question answering over large knowledge bases for applications requiring high accuracy and generalization, representing a strong incremental improvement.
The paper tackles the problem of improving coverage and generalization in knowledge base question answering (KBQA) by introducing TIARA, a model that uses multi-grained retrieval and constrained decoding. It achieves state-of-the-art results, outperforming previous methods by at least 4.1 F1 points on GrailQA and 1.1 F1 points on WebQuestionsSP.
Pre-trained language models (PLMs) have shown their effectiveness in multiple scenarios. However, KBQA remains challenging, especially regarding coverage and generalization settings. This is due to two main factors: i) understanding the semantics of both questions and relevant knowledge from the KB; ii) generating executable logical forms with both semantic and syntactic correctness. In this paper, we present a new KBQA model, TIARA, which addresses those issues by applying multi-grained retrieval to help the PLM focus on the most relevant KB contexts, viz., entities, exemplary logical forms, and schema items. Moreover, constrained decoding is used to control the output space and reduce generation errors. Experiments over important benchmarks demonstrate the effectiveness of our approach. TIARA outperforms previous SOTA, including those using PLMs or oracle entity annotations, by at least 4.1 and 1.1 F1 points on GrailQA and WebQuestionsSP, respectively.