Explicit Memory Tracker with Coarse-to-Fine Reasoning for Conversational Machine Reading

@article{Gao2020ExplicitMT,
  title={Explicit Memory Tracker with Coarse-to-Fine Reasoning for Conversational Machine Reading},
  author={Yifan Gao and Chien-Sheng Wu and Shafiq R. Joty and Caiming Xiong and R. Socher and Irwin King and M. Lyu and S. Hoi},
  journal={ArXiv},
  year={2020},
  volume={abs/2005.12484}
}
The goal of conversational machine reading is to answer user questions given a knowledge base text which may require asking clarification questions. Existing approaches are limited in their decision making due to struggles in extracting question-related rules and reasoning about them. In this paper, we present a new framework of conversational machine reading that comprises a novel Explicit Memory Tracker (EMT) to track whether conditions listed in the rule text have already been satisfied to… Expand
Discern: Discourse-Aware Entailment Reasoning Network for Conversational Machine Reading
Exploring Machine Reading Comprehension for Continuous Questions via Subsequent Question Completion

References

SHOWING 1-10 OF 29 REFERENCES
Interpretation of Natural Language Rules in Conversational Machine Reading
Tracking the World State with Recurrent Entity Networks
Unified Language Model Pre-training for Natural Language Understanding and Generation
Adam: A Method for Stochastic Optimization
Attending to Future Tokens For Bidirectional Sequence Generation
E3: Entailment-driven Extracting and Editing for Conversational Machine Reading
HuggingFace's Transformers: State-of-the-art Natural Language Processing
...
1
2
3
...