Papers by Christoph Alt
TACRED Revisited: A Thorough Evaluation of the TACRED Relation Extraction Task (2020.acl-main)
Copied to clipboard
| Challenge: | Existing methods for Relation Extraction (RE) still show a high error rate . label errors account for 8% absolute F1 test error, and more than 50% of examples need to be relabeled. |
| Approach: | They validate the most challenging 5K examples using trained annotators and analyze misclassifications on the challenging instances. |
| Outcome: | The proposed methods perform well on the most challenging datasets and improve on the relabeled test set. |
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. |
Fine-tuning Pre-Trained Transformer Language Models to Distantly Supervised Relation Extraction (P19-1)
Copied to clipboard
| Challenge: | Current relation extraction methods suffer from noisy labels and incomplete knowledge base information. |
| Approach: | They propose a pre-trained language model that captures semantic and syntactic features and a significant amount of “common-sense” knowledge. |
| Outcome: | The proposed model achieves state-of-the-art AUC score of 0.422 on the NYT10 dataset and performs especially well at higher recall levels. |
Probing Linguistic Features of Sentence-Level Representations in Neural Relation Extraction (2020.acl-main)
Copied to clipboard
| Challenge: | Neural relation extraction models capture linguistic and semantic properties of the input, a recent study shows. |
| Approach: | They introduce 14 probing tasks targeting linguistic properties relevant to RE . they add contextualized word representations to enhance probing performance . |
| Outcome: | The proposed models achieve state-of-the-art on two datasets, TACRED and SemEval 2010 Task 8 . they show that the models capture linguistic and semantic properties relevant to the downstream task . |