Folgen
Nikolaos Pappas
Nikolaos Pappas
Amazon (AWS AI Labs)
Bestätigte E-Mail-Adresse bei amazon.com - Startseite
Titel
Zitiert von
Zitiert von
Jahr
Transformers are RNNs: Fast autoregressive transformers with linear attention
A Katharopoulos, A Vyas, N Pappas, F Fleuret
Thirty-seventh International Conference on Machine Learning (ICML), 2020
11182020
Document-level neural machine translation with hierarchical attention networks
L Miculicich, D Ram, N Pappas, J Henderson
Conference on Empirical Methods in Natural Language Processing (EMNLP), 2018
2942018
Random feature attention
H Peng, N Pappas, D Yogatama, R Schwartz, NA Smith, L Kong
International Conference on Learning Representations (ICLR), 2021
2792021
Deep encoder, shallow decoder: Reevaluating non-autoregressive machine translation
J Kasai, N Pappas, H Peng, J Cross, NA Smith
International Conference on Learning Representations (ICLR), 2021
1592021
Visual affect around the world: A large-scale multilingual visual sentiment ontology
B Jou, T Chen, N Pappas, M Redi, M Topkara, SF Chang
23rd ACM International Conference on Multimedia (MM), 159-168, 2015
1572015
Multilingual hierarchical attention networks for document classification
N Pappas, A Popescu-Belis
8th International Joint Conference on Natural Language Processing (IJCNLP), 2017
1372017
Sentiment analysis of user comments for one-class collaborative filtering over TED talks
N Pappas, A Popescu-Belis
36th International ACM SIGIR Conference on Research and Development in …, 2013
1162013
GILE: A generalized input-label embedding for text classification
N Pappas, J Henderson
Transactions of the Association for Computational Linguistics (TACL) 7, 139-155, 2019
802019
Explaining the stars: Weighted multiple-instance learning for aspect-based sentiment analysis
N Pappas, A Popescu-Belis
Conference on Empirical Methods In Natural Language Processing (EMNLP), 455-466, 2014
732014
Explicit document modeling through weighted multiple-instance learning
N Pappas, A Popescu-Belis
Journal of Artificial Intelligence Research (JAIR) 58, 591-626, 2017
592017
Combining content with user preferences for TED lecture recommendation
N Pappas, A Popescu-Belis
11th International Workshop on Content Based Multimedia Indexing (CBMI), 2013
412013
Finetuning pretrained transformers into RNNs
J Kasai, H Peng, Y Zhang, D Yogatama, G Ilharco, N Pappas, Y Mao, ...
Conference on Empirical Methods in Natural Language Processing (EMNLP), 2021
392021
Integrating weakly supervised word sense disambiguation into neural machine translation
X Pu, N Pappas, J Henderson, A Popescu-Belis
Transactions of the Association for Computational Linguistics (TACL) 6, 635-649, 2018
392018
Adaptive sentiment-aware one-class collaborative filtering
N Pappas, A Popescu-Belis
Expert Systems with Applications (ESWA), 2015
322015
Plug and play autoencoders for conditional text generation
F Mai, N Pappas, I Montero, NA Smith, J Henderson
Conference on Empirical Methods in Natural Language Processing (EMNLP), 2020
302020
Distinguishing the popularity between topics: A system for up-to-date opinion retrieval and mining in the web
N Pappas, G Katsimpras, E Stamatatos
14th International Conference on Intelligent Text Processing and …, 2013
302013
Self-attentive residual decoder for neural machine translation
LM Werlen, N Pappas, D Ram, A Popescu-Belis
Proceedings of the 2018 Conference of the North American Chapter of the …, 2018
262018
Multi-factor segmentation for topic visualization and recommendation: the must-vis system
CA Bhatt, A Popescu-Belis, M Habibi, S Ingram, S Masneri, F McInnes, ...
21st ACM International Conference on Multimedia (MM), 365-368, 2013
262013
Combining content with user preferences for non-fiction multimedia recommendation: A study on TED lectures
N Pappas, A Popescu-Belis
Multimedia Tools and Applications (MTAP), 2015
252015
Sentence bottleneck autoencoders from transformer language models
I Montero, N Pappas, NA Smith
Conference on Empirical Methods in Natural Language Processing (EMNLP), 2021
202021
Das System kann den Vorgang jetzt nicht ausführen. Versuchen Sie es später erneut.
Artikel 1–20