Understanding time is an important aspect of natural language processing (NLP), whose essential components are understanding the time expressions mentioned in text ("yesterday", "this June", etc.), temporal relations (before, after, overlapping, etc.) between events, time-lining events, figuring out when things happened and how long things take. Little work has been done from the NLP perspective in this domain, which is increasingly important with the rapid growth in natural language text available and in social media volume.
- "Going on a vacation" takes longer than "Going for a walk": A Study of Temporal Commonsense Understanding
- An Improved Neural Baseline for Temporal Relation Extraction
- Partial or Complete, That's The Question
- CogCompTime: A Tool for Understanding Time in Natural Language
- Joint Reasoning for Temporal and Causal Relations
- A Multi-Axis Annotation Scheme for Event Temporal Relations
- Exploiting Partially Annotated Data for Temporal Relation Extraction
- Improving Temporal Relation Extraction with a Globally Acquired Statistical Resource
- A Structured Learning Approach to Temporal Relation Extraction