DE eng

Search in the Catalogues and Directories

Page: 1 2
Hits 1 – 20 of 22

1
Estimating the Entropy of Linguistic Distributions ...
BASE
Show details
2
On Homophony and Rényi Entropy ...
BASE
Show details
3
On Homophony and Rényi Entropy ...
BASE
Show details
4
On Homophony and Rényi Entropy ...
BASE
Show details
5
Searching for Search Errors in Neural Morphological Inflection ...
BASE
Show details
6
Revisiting the Uniform Information Density Hypothesis ...
BASE
Show details
7
Revisiting the Uniform Information Density Hypothesis ...
BASE
Show details
8
Conditional Poisson Stochastic Beams ...
BASE
Show details
9
Language Model Evaluation Beyond Perplexity ...
BASE
Show details
10
A surprisal--duration trade-off across and within the world's languages ...
BASE
Show details
11
Determinantal Beam Search ...
BASE
Show details
12
Is Sparse Attention more Interpretable? ...
BASE
Show details
13
Revisiting the Uniform Information Density Hypothesis ...
BASE
Show details
14
A Plug-and-Play Method for Controlled Text Generation ...
BASE
Show details
15
Language Model Evaluation Beyond Perplexity ...
Meister, Clara Isabel; Cotterell, Ryan. - : ETH Zurich, 2021
BASE
Show details
16
Determinantal Beam Search ...
BASE
Show details
17
Is Sparse Attention more Interpretable? ...
BASE
Show details
18
A Cognitive Regularizer for Language Modeling ...
Abstract: The uniform information density (UID) hypothesis, which posits that speakers behaving optimally tend to distribute information uniformly across a linguistic signal, has gained traction in psycholinguistics as an explanation for certain syntactic, morphological, and prosodic choices. In this work, we explore whether the UID hypothesis can be operationalized as an inductive bias for statistical language modeling. Specifically, we augment the canonical MLE objective for training language models with a regularizer that encodes UID. In experiments on ten languages spanning five language families, we find that using UID regularization consistently improves perplexity in language models, having a larger effect when training data is limited. Moreover, via an analysis of generated sequences, we find that UID-regularized language models have other desirable properties, e.g., they generate text that is more lexically diverse. Our results not only suggest that UID is a reasonable inductive bias for language modeling, ... : ACL 2021 Camera-ready (fixed ordering of affiliation emojis) ...
Keyword: Computation and Language cs.CL; FOS Computer and information sciences
URL: https://dx.doi.org/10.48550/arxiv.2105.07144
https://arxiv.org/abs/2105.07144
BASE
Hide details
19
A Cognitive Regularizer for Language Modeling ...
BASE
Show details
20
A Cognitive Regularizer for Language Modeling ...
BASE
Show details

Page: 1 2

Catalogues
0
0
0
0
0
0
0
Bibliographies
0
0
0
0
0
0
0
0
0
Linked Open Data catalogues
0
Online resources
0
0
0
0
Open access documents
22
0
0
0
0
© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern