Open question answering over curated and extracted knowledge bases

@inproceedings{2014OpenQA,
  title={Open question answering over curated and extracted knowledge bases},
  author={},
  booktitle={KDD},
  year={2014}
}
We consider the problem of open-domain question answering (Open QA) over massive knowledge bases (KBs). Existing approaches use either manually curated KBs like Freebase or KBs automatically extracted from unstructured text. In this paper, we present OQA, the first approach to leverage both curated and extracted KBs. A key technical challenge is designing systems that are robust to the high variability in both natural language questions and massive KBs. OQA achieves robustness by decomposing… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 215 CITATIONS

Constructing lexicons of relational phrases

VIEW 9 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

Learning to Paraphrase for Question Answering

VIEW 10 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Open Question Answering

VIEW 23 EXCERPTS
CITES RESULTS & BACKGROUND

Learning natural language interfaces with neural models

VIEW 4 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Question Answering on Canonicalized Knowledge Base

Cheng Chen Caspar, Xiyang Feng Andy, Qianli Song
  • 2018
VIEW 4 EXCERPTS
HIGHLY INFLUENCED