Temporal Common Sense Acquisition with Minimal Supervision

@article{Zhou2020TemporalCS,
  title={Temporal Common Sense Acquisition with Minimal Supervision},
  author={Ben Zhou and Qiang Ning and Daniel Khashabi and D. Roth},
  journal={ArXiv},
  year={2020},
  volume={abs/2005.04304}
}
Temporal common sense (e.g., duration and frequency of events) is crucial for understanding natural language. However, its acquisition is challenging, partly because such information is often not expressed explicitly in text, and human annotation on such concepts is costly. This work proposes a novel sequence modeling approach that exploits explicit and implicit mentions of temporal common sense, extracted from a large corpus, to build TACOLM, a temporal common sense language model. Our method… Expand
17 Citations
Joint Constrained Learning for Event-Event Relation Extraction
  • 10
  • PDF
Improving Event Duration Prediction via Time-aware Pre-training
  • PDF
CoCoLM: COmplex COmmonsense Enhanced Language Model
  • 1
  • PDF
SpartQA: : A Textual Question Answering Benchmark for Spatial Reasoning
  • PDF
Temporal Reasoning in Natural Language Inference
  • 2
  • PDF
TransOMCS: From Linguistic Graphs to Commonsense Knowledge
  • 13
  • PDF
Acquisition of Periodic Events with Person Attributes
Do Language Embeddings capture Scales?
  • PDF
Microtask Detection
  • 1
  • PDF
...
1
2
...

References

SHOWING 1-10 OF 46 REFERENCES
Improving Temporal Relation Extraction with a Globally Acquired Statistical Resource
  • 26
  • PDF
Ordinal Common-sense Inference
  • 72
  • PDF
A Structured Learning Approach to Temporal Relation Extraction
  • 42
  • PDF
CogCompTime: A Tool for Understanding Time in Natural Language
  • 16
  • PDF
Using Query Patterns to Learn the Duration of Events
  • 35
  • PDF
Temporal Information Extraction by Predicting Relative Time-lines
  • 13
  • PDF
KnowSemLM: A Knowledge Infused Semantic Language Model
  • 5
  • PDF
Deep contextualized word representations
  • 5,692
  • PDF
Extracting implicit knowledge from text
  • 20
Fine-Grained Temporal Relation Extraction
  • 22
  • Highly Influential
  • PDF
...
1
2
3
4
5
...