1 |
Shapley Idioms: Analysing BERT Sentence Embeddings for General Idiom Token Identification
|
|
|
|
In: Front Artif Intell (2022)
|
|
BASE
|
|
Show details
|
|
2 |
Poisoning Knowledge Graph Embeddings via Relation Inference Patterns ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
Poisoning Knowledge Graph Embeddings via Relation Inference Patterns ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
Adversarial Attacks on Knowledge Graph Embeddings via Instance Attribution Methods ...
|
|
|
|
Abstract:
Anthology paper link: https://aclanthology.org/2021.emnlp-main.648/ Abstract: Despite the widespread use of Knowledge Graph Embeddings (KGE), little is known about the security vulnerabilities that might disrupt their intended behaviour. We study data poisoning attacks against KGE models for link prediction. These attacks craft adversarial additions or deletions at training time to cause model failure at test time. To select adversarial deletions, we propose to use the model-agnostic instance attribution methods from Interpretable Machine Learning, which identify the training instances that are most influential to a neural model’s predictions on test instances. We use these influential triples as adversarial deletions. We further propose a heuristic method to replace one of the two entities in each influential triple to generate adversarial additions. Our experiments show that the proposed strategies outperform the state-of-art data poisoning attacks on KGE models and improve the MRR degradation due to the ...
|
|
Keyword:
Computational Linguistics; Machine Learning; Machine Learning and Data Mining; Natural Language Processing
|
|
URL: https://underline.io/lecture/37751-adversarial-attacks-on-knowledge-graph-embeddings-via-instance-attribution-methods https://dx.doi.org/10.48448/bvyg-qk30
|
|
BASE
|
|
Hide details
|
|
5 |
Style versus Content: A distinction without a (learnable) difference?
|
|
|
|
In: International Conference on Computational Linguistics ; https://hal.archives-ouvertes.fr/hal-03112354 ; International Conference on Computational Linguistics, Dec 2020, Virtual, Spain (2020)
|
|
BASE
|
|
Show details
|
|
6 |
Language-Driven Region Pointer Advancement for Controllable Image Captioning ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
English WordNet Taxonomic Random Walk Pseudo-Corpora
|
|
|
|
In: Conference papers (2020)
|
|
BASE
|
|
Show details
|
|
9 |
Language-Driven Region Pointer Advancement for Controllable Image Captioning
|
|
|
|
In: Conference papers (2020)
|
|
BASE
|
|
Show details
|
|
10 |
Local Alignment of Frame of Reference Assignment in English and Swedish Dialogue
|
|
|
|
In: Conference papers (2020)
|
|
BASE
|
|
Show details
|
|
12 |
Synthetic, Yet Natural: Properties of WordNet Random Walk Corpora and the impact of rare words on embedding performance
|
|
|
|
In: Conference papers (2019)
|
|
BASE
|
|
Show details
|
|
13 |
Size Matters: The Impact of Training Size in Taxonomically-Enriched Word Embeddings
|
|
|
|
In: Articles (2019)
|
|
BASE
|
|
Show details
|
|
14 |
TEST: A terminology extraction system for technology related terms
|
|
|
|
In: Conference papers (2019)
|
|
BASE
|
|
Show details
|
|
15 |
Modular Mechanistic Networks: On Bridging Mechanistic and Phenomenological Models with Deep Neural Networks in Natural Language Processing ...
|
|
|
|
BASE
|
|
Show details
|
|
16 |
What is not where: the challenge of integrating spatial representations into deep learning architectures ...
|
|
|
|
BASE
|
|
Show details
|
|
17 |
Is it worth it? Budget-related evaluation metrics for model selection ...
|
|
|
|
BASE
|
|
Show details
|
|
18 |
Is it worth it? Budget-related evaluation metrics for model selection
|
|
|
|
In: Conference papers (2018)
|
|
BASE
|
|
Show details
|
|
19 |
Exploring the Functional and Geometric Bias of Spatial Relations Using Neural Language Models
|
|
|
|
In: Conference papers (2018)
|
|
BASE
|
|
Show details
|
|
20 |
Idiom Type Identification with Smoothed Lexical Features and a Maximum Margin Classifier ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|