paper-with-me

홈 › Papers

The emergent algebraic structure of RNNs and embeddings in NLP

2018-03-07 · Sean A. Cantrell

We examine the algebraic and geometric properties of a uni-directional GRU and word embeddings trained end-to-end on a text classification task. A hyperparameter search over word embedding dimension, GRU hidden dimension, and a linear combination of the GRU outputs is performed. We conclude that words naturally embed themselves in a Lie group and that RNNs form a nonlinear representation of the group. Appealing to these results, we propose a novel class of recurrent-like neural networks and a word embedding scheme.

📄 PDF Abstract BibTeX arXiv:1803.02839

Code (0)

등록된 구현이 없습니다.

Tasks

General Classificationtext-classificationText ClassificationWord Embeddings

Methods 이 논문이 사용한 방법론

GRU A Gated Recurrent Unit, or GRU, is a type of recurrent neural network. It is similar to an LSTM, but only has two gates - a reset…

Similar Papers 제목 키워드 기반

Native Hierarchical and Compositional Representations with Subspace Embeddings

2025-08-21 · Gabriel Moreira, Zita Marinho, Manuel Marques, João Paulo Costeira 외 arxiv

Traditional embeddings represent datapoints as vectors, which makes similarity easy to compute but limits how well they capture hierarchies and compositionality. We propose a fundamentally different approach: representin…

Natural Language Inference

Uncovering Meanings of Embeddings via Partial Orthogonality

2023-10-26 · NeurIPS 2023 11

Machine learning tools often rely on embedding text as vectors of real numbers. In this paper, we study how the semantic structure of language is encoded in the algebraic structure of such embeddings. Specifically, we lo…

Probing sentence embeddings for structure-dependent tense

2018-11-01 · WS 2018 11 · Geoff Bacon, Terry Regier

Learning universal sentence representations which accurately model sentential semantic content is a current goal of natural language processing research. A prominent and successful approach is to train recurrent neural n…

SentenceSentence Embeddings

Transport of Algebraic Structure to Latent Embeddings

2024-05-27 · Samuel Pfrommer, Brendon G. Anderson, Somayeh Sojoudi

Machine learning often aims to produce latent embeddings of inputs which lie in a larger, abstract mathematical space. For example, in the field of 3D modeling, subsets of Euclidean space can be embedded as vectors using…

Linear Spaces of Meanings: Compositional Structures in Vision-Language Models

2023-02-28 · ICCV 2023 1 · Matthew Trager, Pramuditha Perera, Luca Zancato, Alessandro Achille 외

We investigate compositional structures in data embeddings from pre-trained vision-language models (VLMs). Traditionally, compositionality has been associated with algebraic operations on embeddings of words from a pre-e…

DisentanglementRetrieval