# Improving Question Answering over Incomplete KBs with Knowledge-Aware Reader

Source: [Improving Question Answering over Incomplete KBs with Knowledge-Aware Reader](<https://www.sota2.com/research/paper/68fa65dc1e209131cea0ce13>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T21:37:37.790Z

Authors: Wenhan Xiong, Mo Yu, Shiyu Chang, Xiaoxiao Guo, William Yang Wang

Published: 2019-05-17T03:00:46.000Z

## Abstract

We propose a new end-to-end question answering model, which learns to aggregate answer evidence from an incomplete knowledge base (KB) and a set of retrieved text snippets. Under the assumptions that the structured KB is easier to query and the acquired knowledge can help the understanding of unstructured text, our model first accumulates knowledge of entities from a question-related KB subgraph; then reformulates the question in the latent space and reads the texts with the accumulated entity knowledge at hand. The evidence from KB and texts are finally aggregated to predict answers. On the widely-used KBQA benchmark WebQSP, our model achieves consistent improvements across settings with different extents of KB incompleteness.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Knowledge Graph Question Answering on WebQSP](<https://www.sota2.com/research/sota/knowledge-graph-question-answering-on-webqsp.md>): Knowledge Graph Question Answering; WebQSP; Hit@1: 67.2.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1905.07098>)

[PDF](<https://arxiv.org/pdf/1905.07098.pdf>)