Exploring Markov Logic Networks for Question Answering

@inproceedings{Khot2015ExploringML,
  title={Exploring Markov Logic Networks for Question Answering},
  author={Tushar Khot and Niranjan Balasubramanian and Eric Gribkoff and Ashish Sabharwal and P. Clark and Oren Etzioni},
  booktitle={EMNLP},
  year={2015}
}
Elementary-level science exams pose significant knowledge acquisition and reasoning challenges for automatic question answering. [...] Key Method First, we simply use the extracted science rules directly as MLN clauses and exploit the structure present in hard constraints to improve tractability. Second, we interpret science rules as describing prototypical entities, resulting in a drastically simplified but brittle network.Expand
Combining Retrieval, Statistics, and Inference to Answer Elementary Science Questions
Reasoning-Driven Question-Answering for Natural Language Understanding
Taking a Closed-Book Examination: Decoupling KB-Based Inference by Virtual Hypothesis for Answering Real-World Questions
Answering Complex Questions Using Open Information Extraction
Tables as Semi-structured Knowledge for Question Answering
Fine-Grained Explanations Using Markov Logic
...
1
2
3
4
...

References

SHOWING 1-10 OF 25 REFERENCES
Memory-Efficient Inference in Relational Domains
Efficient Markov Logic Inference for Natural Language Semantics
  • Iz Beltagy, R. Mooney
  • Computer Science
  • AAAI Workshop: Statistical Relational Artificial Intelligence
  • 2014
Tuffy: Scaling up Statistical Inference in Markov Logic Networks using an RDBMS
Constraint Propagation for Efficient Inference in Markov Logic
A Study of the AKBC Requirements for Passing an Elementary Science Test
Sound and Efficient Inference with Probabilistic and Deterministic Dependencies
Predicting Learnt Clauses Quality in Modern SAT Solvers
Lifted First-Order Probabilistic Inference
Entity Resolution with Markov Logic
...
1
2
3
...