DE eng

Search in the Catalogues and Directories

Hits 1 – 8 of 8

1
On Homophony and Rényi Entropy ...
BASE
Show details
2
Revisiting the Uniform Information Density Hypothesis ...
BASE
Show details
3
Conditional Poisson Stochastic Beams ...
BASE
Show details
4
Differentiable Subset Pruning of Transformer Heads ...
Abstract: Multi-head attention, a collection of several attention mechanisms that independently attend to different parts of the input, is the key ingredient in the Transformer. Recent work has shown, however, that a large proportion of the heads in a Transformer's multi-head attention mechanism can be safely pruned away without significantly harming the performance of the model; such pruning leads to models that are noticeably smaller and faster in practice. Our work introduces a new head pruning technique that we term differentiable subset pruning. Intuitively, our method learns per-head importance variables and then enforces a user-specified hard constraint on the number of unpruned heads. The importance variables are learned via stochastic gradient descent. We conduct experiments on natural language inference and machine translation; we show that differentiable subset pruning performs comparably or better than previous works while offering precise control of the sparsity level. ...
Keyword: Computational Linguistics; Machine Learning; Machine Learning and Data Mining; Natural Language Processing
URL: https://underline.io/lecture/38190-differentiable-subset-pruning-of-transformer-heads
https://dx.doi.org/10.48448/bk2x-zy23
BASE
Hide details
5
A Bayesian Framework for Information-Theoretic Probing ...
BASE
Show details
6
Classifying Dyads for Militarized Conflict Analysis ...
BASE
Show details
7
A surprisal--duration trade-off across and within the world's languages ...
BASE
Show details
8
On the Relationships Between the Grammatical Genders of Inanimate Nouns and Their Co-Occurring Adjectives and Verbs ...
BASE
Show details

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
8
0
0
0
0
© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern