Ruslan Salakhutdinov, Yingbo Zhou, Kazuma Hashimoto, Alan Black, Shrimai Prabhumoye
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Document grounded generation is the task of using the information provided in a document to improve text generation. This work focuses on two different document grounded generation tasks: Wikipedia Update Generation task and Dialogue response generation. Our work introduces two novel adaptations of large scale pre-trained encoder-decoder models focusing on building context driven representation of the document and enabling specific attention to the information in the document. Additionally, we provide a stronger BART baseline for these tasks. Our proposed techniques outperform existing methods on both automated (at least 48% increase in BLEU-4 points) and human evaluation for closeness to reference and relevance to the document. Furthermore, we perform comprehensive manual inspection of the generated output and categorize errors to provide insights into future directions in modeling these tasks.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2104.12714")
get_code_for_paper("2104.12714")
have("2104.12714")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2104.12714.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2104.12714)
Connect an agent — have() is free.