Papers by Christoph Meinel
Mark-Evaluate: Assessing Language Generation using Population Estimation Methods (2020.coling-main)
Copied to clipboard
| Challenge: | Existing population estimation methods focus on open populations or closed populations, but our methods show a higher correlation to human evaluation than existing metrics on several challenging tasks. |
| Approach: | They propose a family of metrics to assess language generation derived from population estimation methods widely used in ecology. |
| Outcome: | The proposed methods show a higher correlation to human evaluation than existing metrics on several challenging tasks, namely unconditional language generation, machine translation, and text summarization. |
Best Student Forcing: A Simple Training Mechanism in Adversarial Language Generation (2020.lrec-1)
Copied to clipboard
| Challenge: | Language models trained with Maximum Likelihood Estimation (MLE) have been considered as a mainstream solution in Natural Language Generation (NLG) however, they are reportedly suffering from training instability and mode collapse, and therefore outperform conventional MLE models. |
| Approach: | They propose a method to improve Generative Adversarial Nets (GANs) using best student forcing and discriminators to increase training stability and sample diversity. |
| Outcome: | The proposed techniques outperform MLE models and outperformed existing approaches in terms of sample diversity and training stability. |
PubMedCLIP: How Much Does CLIP Benefit Visual Question Answering in the Medical Domain? (2023.findings-eacl)
Copied to clipboard
| Challenge: | Medical visual question answering is a multimodal task that requires a system to understand both medical images and textual questions and infer associations between them. |
| Approach: | They propose a fine-tuned version of CLIP for the medical domain based on PubMed articles. |
| Outcome: | The proposed model improves accuracy up to 3% on two MedVQA benchmark datasets. |