paper-with-me

홈 › Papers

Interpolated Spectral NGram Language Models

2019-07-01 · ACL 2019 7 · Ariadna Quattoni, Xavier Carreras

Spectral models for learning weighted non-deterministic automata have nice theoretical and algorithmic properties. Despite this, it has been challenging to obtain competitive results in language modeling tasks, for two main reasons. First, in order to capture long-range dependencies of the data, the method must use statistics from long substrings, which results in very large matrices that are difficult to decompose. The second is that the loss function behind spectral learning, based on moment matching, differs from the probabilistic metrics used to evaluate language models. In this work we employ a technique for scaling up spectral learning, and use interpolated predictions that are optimized to maximize perplexity. Our experiments in character-based language modeling show that our method matches the performance of state-of-the-art ngram models, while being very fast to train.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage Modelling

Methods 이 논문이 사용한 방법론

Affine Coupling 설명 없음
Normalizing Flows Normalizing Flows are a method for constructing complex distributions by transforming a probability density through a series of invertible mappings. By repeatedly applying…

Similar Papers 제목 키워드 기반

A Targeted Assessment of Incremental Processing in Neural LanguageModels and Humans

2021-06-06 · Ethan Gotlieb Wilcox, Pranali Vani, Roger P. Levy

We present a targeted, scaled-up comparison of incremental processing in humans and neural language models by collecting by-word reaction time data for sixteen different syntactic test suites across a range of structural…

Language ModelingLanguage ModellingSentence

A Targeted Assessment of Incremental Processing in Neural Language Models and Humans

2021-08-01 · ACL 2021 5 · Ethan Wilcox, Pranali Vani, Roger Levy

We present a targeted, scaled-up comparison of incremental processing in humans and neural language models by collecting by-word reaction time data for sixteen different syntactic test suites across a range of structural…

Language ModelingLanguage ModellingSentence

Beyond the Laplacian: Interpolated Spectral Augmentation for Graph Neural Networks

2025-11-14 · Ziyao Cui, Edric Tam arxiv

Graph neural networks (GNNs) are fundamental tools in graph machine learning. The performance of GNNs relies crucially on the availability of informative node features, which can be limited or absent in real-life dataset…

Lngram: N-gram Conditional Memory in Latent Space

2026-05-24 · Yunao Zheng, Guoyang Xia, Xiaojie Wang, Lei Ren arxiv

Sequence modeling requires both compositional reasoning and local static knowledge retrieval, yet standard Transformers handle both through dense computation. Engram partially decouples retrieval from the backbone, but i…

Improved Hyperspectral Unmixing With Endmember Variability Parametrized Using an Interpolated Scaling Tensor

2019-01-02 · Ricardo Augusto Borsoi, Tales Imbiriba, José Carlos Moreira Bermudez

Endmember (EM) variability has an important impact on the performance of hyperspectral image (HI) analysis algorithms. Recently, extended linear mixing models have been proposed to account for EM variability in the spect…

Hyperspectral Unmixing