• Computer Science
  • Published in ArXiv 2019

A Generate-Validate Approach to Answering Questions about Qualitative Relationships

@article{Mitra2019AGA,
  title={A Generate-Validate Approach to Answering Questions about Qualitative Relationships},
  author={Arindam Mitra and Chitta Baral and Aurgho Bhattacharjee and Ishan Shrivastava},
  journal={ArXiv},
  year={2019},
  volume={abs/1908.03645}
}
Qualitative relationships describe how increasing or decreasing one property (e.g. altitude) affects another (e.g. temperature). They are an important aspect of natural language question answering and are crucial for building chatbots or voice agents where one may enquire about qualitative relationships. Recently a dataset about question answering involving qualitative relationships has been proposed, and a few approaches to answer such questions have been explored, in the heart of which lies a… CONTINUE READING

Tables and Topics from this paper.

References

Publications referenced by this paper.
SHOWING 1-10 OF 19 REFERENCES

Enhanced LSTM for Natural Language Inference

VIEW 8 EXCERPTS
HIGHLY INFLUENTIAL

Recognizing Textual Entailment: Models and Applications

VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

Large-scale Semantic Parsing without Question-Answer Pairs

VIEW 2 EXCERPTS