Papers by Jessica Chen-Burger
In Layman’s Terms: Semi-Open Relation Extraction from Scientific Texts (2020.acl-main)
Copied to clipboard
| Challenge: | Information Extraction (IE) systems extract only a fraction of the information captured, and Open IE systems do not perform well on the long and complex sentences encountered in scientific texts. |
| Approach: | They propose to use Focused Open Biological Information Extraction (FOBIE) to train a narrow scientific IE system to extract trade-off relations and arguments that are central to biology texts. |
| Outcome: | The proposed system extracts trade-off relations and arguments that are central to biology texts. |
A Scientific Information Extraction Dataset for Nature Inspired Engineering (2020.lrec-1)
Copied to clipboard
| Challenge: | Existing approaches to extract relevant biological information from scientific literature are difficult and require domain-specific knowledge. |
| Approach: | They describe a dataset of 1,500 manually-annotated sentences that express domain-independent relations between central concepts in a scientific biology text. |
| Outcome: | The proposed dataset allows for training and evaluation of Relation Extraction algorithms that aim for coarse-grained typing of scientific biological documents, enabling a high-level filter for engineers. |