Papers with TESA an encoder-decoder language model
TESA: A Task in Entity Semantic Aggregation for Abstractive Summarization (2020.emnlp-main)
Copied to clipboard
| Challenge: | Abstractive summarization systems focus on paraphrasing and simplifying the source content, to the exclusion of such semantic abstraction capabilities. |
| Approach: | They propose a dataset and task to fine tune an abstractive summarization model to generate aggregations of 5.3K entities from a crowd-sourced dataset. |
| Outcome: | The proposed task and dataset show that the proposed model can generate aggregations at a semantic level, but that it is too complex to use. |