DE eng

Search in the Catalogues and Directories

Page: 1 2 3 4 5 6...9
Hits 21 – 40 of 163

21
A Bayesian Framework for Information-Theoretic Probing ...
BASE
Show details
22
Classifying Dyads for Militarized Conflict Analysis ...
BASE
Show details
23
Higher-order Derivatives of Weighted Finite-state Machines ...
BASE
Show details
24
On Finding the K-best Non-projective Dependency Trees ...
BASE
Show details
25
A surprisal--duration trade-off across and within the world's languages ...
BASE
Show details
26
Determinantal Beam Search ...
BASE
Show details
27
Is Sparse Attention more Interpretable? ...
BASE
Show details
28
Revisiting the Uniform Information Density Hypothesis ...
BASE
Show details
29
A Plug-and-Play Method for Controlled Text Generation ...
Abstract: Large pre-trained language models have repeatedly shown their ability to produce fluent text. Yet even when starting from a prompt, generation can continue in many plausible directions. Current decoding methods with the goal of controlling generation, e.g., to ensure specific words are included, either require additional models or fine-tuning, or work poorly when the task at hand is semantically unconstrained, e.g., story generation. In this work, we present a plug-and-play decoding method for controlled language generation that is so simple and intuitive, it can be described in a single sentence: given a topic or keyword, we add a shift to the probability distribution over our vocabulary towards semantically similar words. We show how annealing this distribution can be used to impose hard constraints on language generation, something no other plug-and-play method is currently able to do with SOTA language generators. Despite the simplicity of this approach, we see it works incredibly well in practice: ... : Findings of the Association for Computational Linguistics: EMNLP 2021 ...
URL: http://hdl.handle.net/20.500.11850/518988
https://dx.doi.org/10.3929/ethz-b-000518988
BASE
Hide details
30
Language Model Evaluation Beyond Perplexity ...
Meister, Clara Isabel; Cotterell, Ryan. - : ETH Zurich, 2021
BASE
Show details
31
What About the Precedent: An Information-Theoretic Analysis of Common Law ...
BASE
Show details
32
Searching for More Efficient Dynamic Programs ...
Vieira, Tim; Cotterell, Ryan; Eisner, Jason. - : ETH Zurich, 2021
BASE
Show details
33
Modeling the Unigram Distribution ...
BASE
Show details
34
Determinantal Beam Search ...
BASE
Show details
35
Examining the Inductive Bias of Neural Language Models with Artificial Languages ...
White, Jennifer C.; Cotterell, Ryan. - : ETH Zurich, 2021
BASE
Show details
36
Finding Concept-specific Biases in Form–Meaning Associations ...
BASE
Show details
37
Differentiable subset pruning of transformer heads ...
Li, Jiaoda; Cotterell, Ryan; Sachan, Mrinmaya. - : ETH Zurich, 2021
BASE
Show details
38
On Finding the K-best Non-projective Dependency Trees ...
Zmigrod, Ran; Vieira, Tim; Cotterell, Ryan. - : ETH Zurich, 2021
BASE
Show details
39
Efficient computation of expectations under spanning tree distributions ...
Zmigrod, Ran; Vieira, Tim; Cotterell, Ryan. - : ETH Zurich, 2021
BASE
Show details
40
Multimodal pretraining unmasked: A meta-analysis and a unified framework of vision-and-language berts ...
BASE
Show details

Page: 1 2 3 4 5 6...9

Catalogues
0
0
0
0
0
0
1
Bibliographies
0
0
0
0
0
0
0
0
0
Linked Open Data catalogues
0
Online resources
0
0
0
0
Open access documents
162
0
0
0
0
© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern