Answering Complex Questions Using Open Information Extraction

@article{Khot2017AnsweringCQ,
  title={Answering Complex Questions Using Open Information Extraction},
  author={Tushar Khot and Ashish Sabharwal and Peter Clark},
  journal={ArXiv},
  year={2017},
  volume={abs/1704.05572}
}
While there has been substantial progress in factoid question-answering (QA), answering complex questions remains challenging, typically requiring both a large body of knowledge and inference techniques. [...] Key Method We overcome this limitation by presenting a method for reasoning with Open IE knowledge, allowing more complex questions to be handled.Expand
72 Citations
A Near-Real-Time Answer Discovery for Open-Domain With Unanswerable Questions From the Web
  • PDF
QASC: A Dataset for Question Answering via Sentence Composition
  • 48
  • PDF
Reasoning-Driven Question-Answering for Natural Language Understanding
  • Highly Influenced
  • PDF
Improving Question Answering with External Knowledge
  • 30
  • Highly Influenced
  • PDF
Extracting Common Inference Patterns from Semi-Structured Explanations
  • 2
  • PDF
KG^2: Learning to Reason Science Exam Questions with Contextual Knowledge Graph Embeddings
  • 19
  • PDF
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 23 REFERENCES
Question Answering via Integer Programming over Semi-Structured Knowledge
  • 75
  • PDF
Open question answering over curated and extracted knowledge bases
  • 340
  • PDF
Exploring Markov Logic Networks for Question Answering
  • 33
  • PDF
Compositional Semantic Parsing on Semi-Structured Tables
  • 292
  • PDF
Answering Questions with Complex Semantic Constraints on Open Knowledge Bases
  • 57
  • PDF
Semantic Parsing on Freebase from Question-Answer Pairs
  • 1,078
  • PDF
Table Cell Search for Question Answering
  • 69
  • PDF
Paraphrase-Driven Learning for Open Question Answering
  • 287
  • PDF
Combining Retrieval, Statistics, and Inference to Answer Elementary Science Questions
  • 106
  • PDF
Taking Up the Gaokao Challenge: An Information Retrieval Approach
  • 19
  • Highly Influential
  • PDF
...
1
2
3
...