Multi-hop Inference for Sentence-level TextGraphs: How Challenging is Meaningfully Combining Information for Science Question Answering?

@inproceedings{Jansen2018MultihopIF,
  title={Multi-hop Inference for Sentence-level TextGraphs: How Challenging is Meaningfully Combining Information for Science Question Answering?},
  author={Peter Jansen},
  booktitle={TextGraphs@NAACL-HLT},
  year={2018}
}
  • Peter Jansen
  • Published in TextGraphs@NAACL-HLT 2018
  • Computer Science
Question Answering for complex questions is often modeled as a graph construction or traversal task, where a solver must build or traverse a graph of facts that answer and explain a given question. This "multi-hop" inference has been shown to be extremely challenging, with few models able to aggregate more than two facts before being overwhelmed by "semantic drift", or the tendency for long chains of facts to quickly drift off topic. This is a major barrier to current inference models, as even… Expand
18 Citations
Extracting Common Inference Patterns from Semi-Structured Explanations
  • 2
  • Highly Influenced
  • PDF
TextGraphs 2019 Shared Task on Multi-Hop Inference for Explanation Regeneration
  • 18
  • PDF
QASC: A Dataset for Question Answering via Sentence Composition
  • 47
  • PDF
PGL at TextGraphs 2020 Shared Task: Explanation Regeneration using Language and Graph Learning Methods
  • 1
  • PDF
ExplanationLP: Abductive Reasoning for Explainable Science Question Answering
  • 3
  • PDF
Understanding Dataset Design Choices for Multi-hop Reasoning
  • 46
  • PDF
TextGraphs 2020 Shared Task on Multi-Hop Inference for Explanation Regeneration
  • 5
  • Highly Influenced
  • PDF
...
1
2
...

References

SHOWING 1-10 OF 13 REFERENCES
Higher-order Lexical Semantic Models for Non-factoid Answer Reranking
  • 42
  • Highly Influential
  • PDF
Tables as Semi-structured Knowledge for Question Answering
  • 28
  • PDF
Question Answering via Integer Programming over Semi-Structured Knowledge
  • 75
  • Highly Influential
  • PDF
Constructing Datasets for Multi-hop Reading Comprehension Across Documents
  • 243
  • PDF
Controlling Information Aggregation for Complex Question Answering
  • 7
  • PDF
Answering Complex Questions Using Open Information Extraction
  • 70
  • PDF
What's in an Explanation? Characterizing Knowledge and Inference Requirements for Elementary Science Exams
  • 41
  • PDF
Framing QA as Building and Ranking Intersentence Answer Justifications
  • 35
  • PDF
...
1
2
...