Papers by Ivana Balazevic
TuckER: Tensor Factorization for Knowledge Graph Completion (D19-1)
Copied to clipboard
| Challenge: | Knowledge graphs contain only a small subset of all possible facts . link prediction is a task of inferring missing facts based on existing facts - knowledge graphs are expensive and lack of information is needed to add new information. |
| Approach: | They propose a linear model based on Tucker decomposition of knowledge graph triples . they show that the model is expressive and has sufficient bounds on its embedding dimensionalities . |
| Outcome: | The proposed model outperforms state-of-the-art models across standard datasets and acts as a strong baseline for more elaborate models. |
Cutting Down on Prompts and Parameters: Simple Few-Shot Learning with Language Models (2022.findings-acl)
Copied to clipboard
| Challenge: | Prompting language models (LMs) with training examples and task descriptions has been seen as critical to recent successes in few-shot learning. |
| Approach: | They propose to fine tune masked language models with training examples and task descriptions to reduce prompt engineering by using null prompts. |
| Outcome: | The proposed prompts can be used to improve few-shot learning by finetuning only the bias terms while updating only 0.1% of the parameters. |