• Computer Science
  • Published in ICLR 2018

FlowQA: Grasping Flow in History for Conversational Machine Comprehension

@article{Huang2018FlowQAGF,
  title={FlowQA: Grasping Flow in History for Conversational Machine Comprehension},
  author={Hsin-Yuan Huang and Eunsol Choi and Wen-tau Yih},
  journal={ArXiv},
  year={2018},
  volume={abs/1810.06683}
}
Conversational machine comprehension requires the understanding of the conversation history, such as previous question/answer pairs, the document context, and the current question. To enable traditional, single-turn models to encode the history comprehensively, we introduce Flow, a mechanism that can incorporate intermediate representations generated during the process of answering previous questions, through an alternating parallel processing structure. Compared to approaches that concatenate… CONTINUE READING

Figures, Tables, and Topics from this paper.

Citations

Publications citing this paper.
SHOWING 1-10 OF 26 CITATIONS

GRAPHFLOW: EXPLOITING CONVERSATION FLOW

  • MACHINE COMPREHENSION
  • 2019
VIEW 12 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

TT-Net: Topic Transfer-Based Neural Network for Conversational Reading Comprehension

VIEW 20 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

An Empirical Evaluation on Word Embeddings Across Reading Comprehension

VIEW 6 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

BERT with History Answer Embedding for Conversational Question Answering

VIEW 7 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

FlowDelta: Modeling Flow Information Gain in Reasoning for Conversational Machine Comprehension

VIEW 6 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

MC\^2: Multi-perspective Convolutional Cube for Conversational Machine Reading Comprehension

VIEW 5 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

References

Publications referenced by this paper.
SHOWING 1-10 OF 30 REFERENCES

CoQA: A Conversational Question Answering Challenge

VIEW 8 EXCERPTS
HIGHLY INFLUENTIAL

Deep contextualized word representations

VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Long Short-Term Memory

VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

A Qualitative Comparison of CoQA, SQuAD 2.0 and QuAC

VIEW 2 EXCERPTS
HIGHLY INFLUENTIAL