Papers with supervised attention
Human Attention Maps for Text Classification: Do Humans and Neural Networks Focus on the Same Words? (2020.acl-main)
Copied to clipboard
| Challenge: | Attention-based models have been claimed to add interpretability, but little is known about the actual relationships between machine and human attention. |
| Approach: | They conduct the first quantitative assessment of human versus computational attention mechanisms for the text classification task. |
| Outcome: | The proposed models are compared against machine attention maps on a publicly available YELP dataset. |
Generalized Supervised Attention for Text Generation (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing supervised attention methods that use human knowledge to learn better alignments are costly or infeasible. |
| Approach: | They propose a generalized supervised attention method based on quasi alignments that are easier to obtain than ideal alignments. |
| Outcome: | The proposed framework improves generation performance and is robust against errors in attention supervision. |
Rationale-based Learning Using Self-Supervised Narrative Events for Text Summarisation of Interactive Digital Narratives (2024.lrec-main)
Copied to clipboard
| Challenge: | Using rationale-based learning with supervised attention to train text summarisation models on words and sentences surrounding choice points for Interactive Digital Narratives (IDNs) |
| Approach: | They use word-level and sentence-level rationales to focus model training on words and sentences surrounding self-supervised choice points for Interactive Digital Narratives. |
| Outcome: | The proposed model training improves the quality of the summarised text. |