DE eng

Search in the Catalogues and Directories

Page: 1 2 3 4
Hits 1 – 20 of 75

1
On Homophony and Rényi Entropy ...
BASE
Show details
2
On Homophony and Rényi Entropy ...
BASE
Show details
3
On Homophony and Rényi Entropy ...
BASE
Show details
4
Towards Zero-shot Language Modeling ...
BASE
Show details
5
Differentiable Generative Phonology ...
BASE
Show details
6
Finding Concept-specific Biases in Form--Meaning Associations ...
BASE
Show details
7
Searching for Search Errors in Neural Morphological Inflection ...
BASE
Show details
8
Applying the Transformer to Character-level Transduction ...
Wu, Shijie; Cotterell, Ryan; Hulden, Mans. - : ETH Zurich, 2021
BASE
Show details
9
Quantifying Gender Bias Towards Politicians in Cross-Lingual Language Models ...
BASE
Show details
10
Probing as Quantifying Inductive Bias ...
BASE
Show details
11
Revisiting the Uniform Information Density Hypothesis ...
BASE
Show details
12
Revisiting the Uniform Information Density Hypothesis ...
BASE
Show details
13
Conditional Poisson Stochastic Beams ...
BASE
Show details
14
Examining the Inductive Bias of Neural Language Models with Artificial Languages ...
BASE
Show details
15
Modeling the Unigram Distribution ...
BASE
Show details
16
Language Model Evaluation Beyond Perplexity ...
BASE
Show details
17
Differentiable Subset Pruning of Transformer Heads ...
BASE
Show details
18
A Bayesian Framework for Information-Theoretic Probing ...
BASE
Show details
19
Classifying Dyads for Militarized Conflict Analysis ...
BASE
Show details
20
Higher-order Derivatives of Weighted Finite-state Machines ...
Abstract: Read paper: https://www.aclanthology.org/2021.acl-short.32 Abstract: Weighted finite-state machines are a fundamental building block of NLP systems. They have withstood the test of time---from their early use in noisy channel models in the 1990s up to modern-day neurally parameterized conditional random fields. This work examines the computation of higher-order derivatives with respect to the normalization constant for weighted finite-state machines. We provide a general algorithm for evaluating derivatives of all orders, which has not been previously described in the literature. In the case of second-order derivatives, our scheme runs in the optimal O(A^2 N^4) time where A is the alphabet size and N is the number of states. Our algorithm is significantly faster than prior algorithms. Additionally, our approach leads to a significantly faster algorithm for computing second-order expectations, such as covariance matrices and gradients of first-order expectations. ...
URL: https://dx.doi.org/10.48448/b0dp-6v40
https://underline.io/lecture/25998-higher-order-derivatives-of-weighted-finite-state-machines
BASE
Hide details

Page: 1 2 3 4

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
75
0
0
0
0
© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern