A Discrete Hard EM Approach for Weakly Supervised Question Answering

@article{Min2019ADH,
  title={A Discrete Hard EM Approach for Weakly Supervised Question Answering},
  author={Sewon Min and Danqi Chen and Hannaneh Hajishirzi and Luke Zettlemoyer},
  journal={ArXiv},
  year={2019},
  volume={abs/1909.04849}
}
Many question answering (QA) tasks only provide weak supervision for how the answer should be computed. For example, TriviaQA answers are entities that can be mentioned multiple times in supporting documents, while DROP answers can be computed by deriving many different equations from numbers in the reference text. In this paper, we show it is possible to convert such tasks into discrete latent variable learning problems with a precomputed, task-specific set of possible "solutions" (e.g… CONTINUE READING

Figures, Tables, Results, and Topics from this paper.

Key Quantitative Results

  • Table 4 shows that our training method significantly outperforms all the weaklysupervised learning algorithms, including 10% gain over the previous state of the art.

References

Publications referenced by this paper.
SHOWING 1-10 OF 45 REFERENCES

The NarrativeQA Reading Comprehension Challenge

  • Transactions of the Association for Computational Linguistics
  • 2017
VIEW 12 EXCERPTS
HIGHLY INFLUENTIAL

TypeSQL: Knowledge-based Type-Aware Neural Text-to-SQL Generation

Tao Yu, Zifan Li, Zilin Zhang, Rui Zhang, Dragomir R. Radev
  • NAACL-HLT
  • 2018
VIEW 6 EXCERPTS
HIGHLY INFLUENTIAL

Densely Connected Attention Propagation for Reading Comprehension

Yi Tay, Anh Tuan Luu, Siu Cheung Hui, Jian Su
  • NeurIPS
  • 2018
VIEW 14 EXCERPTS
HIGHLY INFLUENTIAL