Papers by Guergana Savova
Measuring Pointwise đť’±-Usable Information In-Context-ly (2023.findings-emnlp)
Copied to clipboard
| Challenge: | In-context learning (ICL) is a new learning paradigm that has gained popularity along with the development of large language models. |
| Approach: | They propose to adapt a recently proposed hardness metric, pointwise V-usable information (PVI), to an in-context version. |
| Outcome: | The proposed hardness metric is compared with the original model and is more efficient because it requires only a few exemplars and does not require fine-tuning. |
Cross-document coreference: An approach to capturing coreference without context (D19-62)
Copied to clipboard
| Challenge: | a cross-document coreference annotation schema was developed to extract timelines in the clinical domain. |
| Approach: | They propose a cross-document coreference annotation schema that is governed by schematic rules to create meaningful and consistent cross- document relations. |
| Outcome: | The proposed approach produces an agreement score of 93.77% for identical relations between the two sets of notes. |
Two-Stage Fine-Tuning for Improved Bias and Variance for Large Pretrained Language Models (2023.acl-long)
Copied to clipboard
| Challenge: | Recent work challenges the bias-variance trade-off . large pretrained models can have large variance and overfit domain-specific data . |
| Approach: | They propose a bias-variance trade-off that implies learning methods need to balance complexity with data size to minimize under-fitting and over-fit. |
| Outcome: | The proposed method achieves strong results on SuperGLUE and clinical information extraction tasks. |
Spotting Spurious Data with Neural Networks (N18-1)
Copied to clipboard
| Challenge: | Existing methods to identify spurious instances require either annotations generated by each individual annotator or both task-specific and instance-type annotations. |
| Approach: | They propose an approach that discriminates instances based on their "difficulty to learn" they use queueing theory and psychology of learning to improve annotations . |
| Outcome: | The proposed methods outperform state-of-the-art baselines and have a MAP of 0.85 and 0.22 in identifying spurious instances in synthetic and carefully-crowdsourced real-world datasets respectively. |