Corpus ID: 202540412

Incidental Supervision from Question-Answering Signals

@article{He2019IncidentalSF,
  title={Incidental Supervision from Question-Answering Signals},
  author={Hangfeng He and Qiang Ning and D. Roth},
  journal={ArXiv},
  year={2019},
  volume={abs/1909.00333}
}
Human annotations are costly for many natural language processing (NLP) tasks, especially for those requiring NLP expertise. [...] Key Result We also find that the representation retrieved from question-answer meaning representation (QAMR) data can almost universally improve on a wide range of tasks, suggesting that such kind of natural language annotations indeed provide unique information on top of modern language models.Expand
Cross-lingual Entity Alignment for Knowledge Graphs with Incidental Supervision from Free Text

References

SHOWING 1-10 OF 45 REFERENCES
Zero-Shot Relation Extraction via Reading Comprehension
Crowdsourcing Question-Answer Meaning Representations
Question Answering as Global Reasoning Over Semantic Abstractions
GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding
Attention-Based Bidirectional Long Short-Term Memory Networks for Relation Classification
SQuAD: 100, 000+ Questions for Machine Comprehension of Text
Supervised Open Information Extraction
Partial Or Complete, That's The Question
Incidental Supervision: Moving beyond Supervised Learning
  • D. Roth
  • Computer Science, Mathematics
  • AAAI
  • 2017
...
1
2
3
4
5
...