Papers with TCSE task
Time-Aware Representation Learning for Time-Sensitive Question Answering (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing QA datasets do not include sufficient time expressions, and language models have difficulty understanding the relationships between time specifiers and numerical values. |
| Approach: | They propose a Time-Context-dependent Span Extraction task and build a time-context dependent data generation framework for model training. |
| Outcome: | The proposed model outperforms baseline models up to 8.5 of the F1-score in the TimeQA dataset. |