DE eng

Search in the Catalogues and Directories

Page: 1 2 3 4 5...113
Hits 1 – 20 of 2.244

1
SDPRA 2021 Shared Task Data ...
Reddy, Saichethan. - : Mendeley, 2021
BASE
Show details
2
SDPRA 2021 Shared Task Data ...
Reddy, Saichethan. - : Mendeley, 2021
BASE
Show details
3
ASCNET - The popularity of Asclepius in times of plagues ...
Glomb, Tomas. - : Open Science Framework, 2021
BASE
Show details
4
Protocol ...
Harvey, Daisy. - : Open Science Framework, 2021
BASE
Show details
5
Assessing neural network understanding of perspectival motion verbs ...
Anderson, Carolyn. - : Open Science Framework, 2021
BASE
Show details
6
MinorityReport ...
Keeble, Liam. - : Open Science Framework, 2021
BASE
Show details
7
Studying Social Identities in Linguistic Style ...
Cork, Alicia. - : Open Science Framework, 2021
BASE
Show details
8
Predicting emotional links between genre, plot, and reader response ...
Sharma, Srishti. - : Open Science Framework, 2021
BASE
Show details
9
Measuring Equity Mindsets and Improvisational Practices Through Language Patterns in Equity Simulations ...
Littenberg-Tobias, Joshua. - : Open Science Framework, 2021
BASE
Show details
10
Normalized Datasets of Harnack’s Reconstruction of Marcion’s Gospel
In: Journal of Open Humanities Data; Vol 7 (2021); 24 ; 2059-481X (2021)
BASE
Show details
11
Normalized Datasets of Klinghardt’s and Nicolotti’s Reconstructions of Marcion’s Gospel
In: Journal of Open Humanities Data; Vol 7 (2021); 32 ; 2059-481X (2021)
BASE
Show details
12
Automatic Language Identification in Code-Switched Hindi-English Social Media Text
In: Journal of Open Humanities Data; Vol 7 (2021); 7 ; 2059-481X (2021)
BASE
Show details
13
Dependency Patterns of Complex Sentences and Semantic Disambiguation for Abstract Meaning Representation Parsing ...
BASE
Show details
14
Phrase-Level Action Reinforcement Learning for Neural Dialog Response Generation ...
Abstract: Read paper: https://www.aclanthology.org/2021.findings-acl.446 Abstract: Defining a sophisticated action space for a dialog agent is essential for efficient training with reinforcement learning (RL). Recent work introduces discrete latent variables to use as an action space; however, a limitation is that a global vector can contain entangled information such as dialog act, sentence structure, and content. This sacrifices the flexibility of the response generation. In this paper, we propose phrase-level action reinforcement learning (PhraseRL), which allows the model to flexibly alter the sentence structure and content with the sequential action selection. Our model first learns to generate useful phrases during the supervised pre-training, and then further trained to form a response by rearranging the phrases with reinforcement learning. Experiments on the MultiWOZ dataset show that our model achieves competitive results with state-of-the-art models on automatic evaluation metrics, indicating that our ...
Keyword: Computational Linguistics; Condensed Matter Physics; Deep Learning; Electromagnetism; FOS Physical sciences; Neural Network; Semantics
URL: https://dx.doi.org/10.48448/ne1y-mg85
https://underline.io/lecture/26537-phrase-level-action-reinforcement-learning-for-neural-dialog-response-generation
BASE
Hide details
15
10D: Phonology, Morphology and Word Segmentation #1 ...
BASE
Show details
16
Sample-efficient Linguistic Generalizations through Program Synthesis: Experiments with Phonology Problems ...
BASE
Show details
17
19th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology - Part 2 ...
BASE
Show details
18
18th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology - Part 1 ...
BASE
Show details
19
SpeakEasy Pronunciation Trainer: Personalized Multimodal Pronunciation Training ...
BASE
Show details
20
The Match-Extend Serialization Algorithm in Multiprecedence ...
BASE
Show details

Page: 1 2 3 4 5...113

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
2.244
0
0
0
0
© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern