paper-with-me

홈 › Papers

Prevalence and recoverability of syntactic parameters in sparse distributed memories

2015-10-21 · Jeong Joon Park, Ronnel Boettcher, Andrew Zhao, Alex Mun, Kevin Yuh, Vibhor Kumar, Matilde Marcolli

We propose a new method, based on Sparse Distributed Memory (Kanerva Networks), for studying dependency relations between different syntactic parameters in the Principles and Parameters model of Syntax. We store data of syntactic parameters of world languages in a Kanerva Network and we check the recoverability of corrupted parameter data from the network. We find that different syntactic parameters have different degrees of recoverability. We identify two different effects: an overall underlying relation between the prevalence of parameters across languages and their degree of recoverability, and a finer effect that makes some parameters more easily recoverable beyond what their prevalence would indicate. We interpret a higher recoverability for a syntactic parameter as an indication of the existence of a dependency relation, through which the given parameter can be determined using the remaining uncorrupted data.

📄 PDF Abstract BibTeX arXiv:1510.06342

Code (0)

등록된 구현이 없습니다.

Tasks

Relation

Similar Papers 제목 키워드 기반

Parts-of-Speech as Emergent Categories in SAE Latent Space

2026-09-24 · Alessandro Bondielli, Lucia Passaro, Serena Auriemma, Alessandro Lenci hf

Sparse AutoEncoders (SAEs) offer a promising way to inspect language model representations, but it is still unclear what kind of linguistic structure their latents expose. We use part-of-speech (PoS) categories as a cont…

On Recoverability of Randomly Compressed Tensors with Low CP Rank

2020-01-08 · Shahana Ibrahim, Xiao Fu, Xingguo Li

Our interest lies in the recoverability properties of compressed tensors under the \textit{canonical polyadic decomposition} (CPD) model. The considered problem is well-motivated in many applications, e.g., hyperspectral…

Compressive SensingVideo Compression

How Linear Is a Transformer Feed-Forward Block? Per-Block Linear Recoverability Is Learned, Not Architectural

2026-06-12 · Stuart Whipp arxiv

Transformer feed-forward networks (FFNs) are often treated as nonlinear stores of computation, yet how nonlinear a trained FFN block actually is has rarely been measured. We treat each FFN as a position-wise input-to-out…

Sparse Recovery With Non-Linear Fourier Features

2020-02-12 · Ayca Ozcelikkale

Random non-linear Fourier features have recently shown remarkable performance in a wide-range of regression and classification applications. Motivated by this success, this article focuses on a sparse non-linear Fourier …

regression

Predictive Prompt Analysis

2025-01-31 · Jae Yong Lee, Sungmin Kang, Shin Yoo

Large Language Models (LLMs) are machine learning models that have seen widespread adoption due to their capability of handling previously difficult tasks. LLMs, due to their training, are sensitive to how exactly a ques…