paper-with-me

Papers

A model for structured information representation in neural networks

2019-03-26

Humans possess the capability to reason at an abstract level and to structure information into abstract categories, but the underlying neural processes have remained unknown. Experimental evidence has recently emerged for the organization of an important aspect of abstract reasoning: for assigning words to semantic roles in a sentence, such as agent (or subject) and patient (or object). Using minimal assumptions, we show how such a binding of words to semantic roles emerges in a generic spiking neural network through Hebbian plasticity. The resulting model is consistent with the experimental data and enables new computational functionalities such as structured information retrieval, copying data, and comparisons. It thus provides a basis for the implementation of more demanding cognitive computations by networks of spiking neurons.

📄 PDF Abstract BibTeX arXiv:1611.03698

Code (0)

등록된 구현이 없습니다.

Tasks

Information RetrievalRetrievalSentence

Similar Papers 제목 키워드 기반

DUET: 2D Structured and Approximately Equivariant Representations

2023-06-28 · Xavier Suau, Federico Danieli, T. Anderson Keller, Arno Blaas 외

Multiview Self-Supervised Learning (MSSL) is based on learning invariances with respect to a set of input transformations. However, invariance partially or totally removes transformation-related information from the repr…

Self-Supervised LearningTransfer Learning

Multiplicative Tree-Structured Long Short-Term Memory Networks for Semantic Representations

2018-06-01 · SEMEVAL 2018 6 · Nam Khanh Tran, Weiwei Cheng

Tree-structured LSTMs have shown advantages in learning semantic representations by exploiting syntactic information. Most existing methods model tree structures by bottom-up combinations of constituent nodes using the s…

Abstract Meaning RepresentationLearning Semantic RepresentationsMachine TranslationRelation Extraction+3

Enhancing Incremental Summarization with Structured Representations

2024-07-21 · EunJeong Hwang, Yichao Zhou, James Bradley Wendt, Beliz Gunel 외

Large language models (LLMs) often struggle with processing extensive input contexts, which can lead to redundant, inaccurate, or incoherent summaries. Recent methods have used unstructured memory to incrementally proces…

Label-Free Model Evaluation with Semi-Structured Dataset Representations

2021-12-01 · Xiaoxiao Sun, Yunzhong Hou, Hongdong Li, Liang Zheng

Label-free model evaluation, or AutoEval, estimates model accuracy on unlabeled test sets, and is critical for understanding model behaviors in various unseen environments. In the absence of image labels, based on datase…

regression

Improving Neural Entity Disambiguation with Graph Embeddings

2019-07-01 · ACL 2019 7 · {\"O}zge Sevgili, Alex Panchenko, er, Chris Biemann

Entity Disambiguation (ED) is the task of linking an ambiguous entity mention to a corresponding entry in a knowledge base. Current methods have mostly focused on unstructured text data to learn representations of entiti…

ArticlesEntity Disambiguation