Papers by David Harbecke
Train, Sort, Explain: Learning to Diagnose Translation Models (N19-4)
Copied to clipboard
| Challenge: | Evaluating translation models is a trade-off between effort and detail. |
| Approach: | They propose to use a neural text classifier to automatically expose systematic differences between human and machine translations to human experts. |
| Outcome: | The proposed method exposes systematic differences between human and machine translations to human experts. |
Layerwise Relevance Visualization in Convolutional Text Graph Classifiers (D19-53)
Copied to clipboard
| Challenge: | Existing explainability methods do not focus on intermediate states in hidden layers of Deep Neural Networks (DNNs). |
| Approach: | They propose a method that visits visible and hidden layers of a deep neural network and projects them onto the interpretable domain. |
| Outcome: | The proposed method yields meaningful layerwise explanations for a GCN sentence classifier. |
Considering Likelihood in NLP Classification Explanations with Occlusion and Language Modeling (2020.acl-srw)
Copied to clipboard
| Challenge: | Existing explanation methods produce invalid or syntactically incorrect data, neglecting the improved abilities of recent NLP models. |
| Approach: | They propose an explanation method that combines occlusion and language models to sample valid and syntactically correct replacements with high likelihood, given the context of the original input. |
| Outcome: | The proposed method can sample valid and syntactically correct replacements with high likelihood, given the context of the original input. |
Multilingual Relation Classification via Efficient and Effective Prompting (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing work on prompt-based multilingual relation classification (RC) uses pre-trained language models with limited resources. |
| Approach: | They propose a prompt-based multilingual relation classification method that constructs relation triples from relation triple labels and requires minimal translation for the class labels. |
| Outcome: | The proposed method outperforms baselines in English-task training in cross-lingual settings and in fully supervised and few-shot scenarios. |
PolBiX: Detecting LLMs’ Political Bias in Fact-Checking through X-phemisms (2025.findings-emnlp)
Copied to clipboard
| Challenge: | a few models show tendencies of political bias, but this is not mitigated by explicitly calling for objectivism in prompts. |
| Approach: | They investigate political bias by exchanging words with euphemisms or dysphemismas in German claims. |
| Outcome: | The proposed model shows that political bias influences truthfulness assessment more than political leaning . |