Inducing Meaningful Units from Character Sequences with Dynamic Capacity Slot Attention
원문 초록
Characters do not convey meaning, but sequences of characters do. We propose an unsupervised distributional method to learn the abstract meaningful units in a sequence of characters. Rather than segmenting the sequence, our Dynamic Capacity Slot Attention model discovers continuous representations of the objects in the sequence, extending an architecture for object discovery in images. We train our model on different languages and evaluate the quality of the obtained representations with forward and reverse probing classifiers. These experiments show that our model succeeds in discovering units which are similar to those proposed previously in form, content and level of abstraction, and which show promise for capturing meaningful information at a higher level of abstraction.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
When Does Pruning Benefit Vision Representations?
Binding threshold units with artificial oscillatory neurons
Are We Done with Object-Centric Learning?
Vector-Quantized Vision Foundation Models for Object-Centric Learning
FrontierNet: Learning Visual Cues to Explore
PickScan: Object discovery and reconstruction from handheld interactions
토론
이 논문과 연결된 포럼 글이 아직 없습니다.