DE eng

Search in the Catalogues and Directories

Page: 1 2
Hits 1 – 20 of 36

1
Universal Dependencies 2.9
Zeman, Daniel; Nivre, Joakim; Abrams, Mitchell. - : Universal Dependencies Consortium, 2021
BASE
Show details
2
Universal Dependencies 2.8.1
Zeman, Daniel; Nivre, Joakim; Abrams, Mitchell. - : Universal Dependencies Consortium, 2021
BASE
Show details
3
Universal Dependencies 2.8
Zeman, Daniel; Nivre, Joakim; Abrams, Mitchell. - : Universal Dependencies Consortium, 2021
BASE
Show details
4
Enhancing Cognitive Models of Emotions with Representation Learning ...
Guo, Yuting; Choi, Jinho. - : arXiv, 2021
BASE
Show details
5
Boosting Cross-Lingual Transfer via Self-Learning with Uncertainty Estimation ...
BASE
Show details
6
Intensionalizing Abstract Meaning Representations: Non-Veridicality and Scope ...
BASE
Show details
7
The Stem Cell Hypothesis: Dilemma behind Multi-Task Learning with Transformer Encoders ...
Abstract: Anthology paper link: https://aclanthology.org/2021.emnlp-main.451/ Abstract: Multi-task learning with transformer encoders (MTL) has emerged as a powerful technique to improve performance on closely-related tasks for both accuracy and efficiency while a question still remains whether or not it would perform as well on tasks that are distinct in nature. We first present MTL results on five NLP tasks, POS, NER, DEP, CON, and SRL, and depict its deficiency over single-task learning. We then conduct an extensive pruning analysis to show that a certain set of attention heads get claimed by most tasks during MTL, who interfere with one another to fine-tune those heads for their own objectives. Based on this finding, we propose the Stem Cell Hypothesis to reveal the existence of attention heads naturally talented for many tasks that cannot be jointly trained to create adequate embeddings for all of those tasks. Finally, we design novel parameter-free probes to justify our hypothesis and demonstrate how attention ...
Keyword: Computational Linguistics; Machine Learning; Machine Learning and Data Mining; Named Entity Recognition; Natural Language Processing
URL: https://underline.io/lecture/37971-the-stem-cell-hypothesis-dilemma-behind-multi-task-learning-with-transformer-encoders
https://dx.doi.org/10.48448/q28e-8k61
BASE
Hide details
8
Levi Graph AMR Parser using Heterogeneous Attention ...
BASE
Show details
9
Zero-Shot Cross-Lingual Machine Reading Comprehension via Inter-sentence Dependency Graph ...
Xu, Liyan; Zhang, Xuchao; Zong, Bo. - : arXiv, 2021
BASE
Show details
10
Universal Dependencies 2.7
Zeman, Daniel; Nivre, Joakim; Abrams, Mitchell. - : Universal Dependencies Consortium, 2020
BASE
Show details
11
Universal Dependencies 2.6
Zeman, Daniel; Nivre, Joakim; Abrams, Mitchell. - : Universal Dependencies Consortium, 2020
BASE
Show details
12
Transformers to Learn Hierarchical Contexts in Multiparty Dialogue for Span-based Question Answering ...
Li, Changmao; Choi, Jinho D.. - : arXiv, 2020
BASE
Show details
13
Universal Dependencies 2.5
Zeman, Daniel; Nivre, Joakim; Abrams, Mitchell. - : Universal Dependencies Consortium, 2019
BASE
Show details
14
Universal Dependencies 2.4
Nivre, Joakim; Abrams, Mitchell; Agić, Željko. - : Universal Dependencies Consortium, 2019
BASE
Show details
15
Automatic Text-based Personality Recognition on Monologues and Multiparty Dialogues Using Attentive Networks and Contextual Embeddings ...
BASE
Show details
16
Universal Dependencies 2.2
In: https://hal.archives-ouvertes.fr/hal-01930733 ; 2018 (2018)
BASE
Show details
17
Universal Dependencies 2.3
Nivre, Joakim; Abrams, Mitchell; Agić, Željko. - : Universal Dependencies Consortium, 2018
BASE
Show details
18
Universal Dependencies 2.2
Nivre, Joakim; Abrams, Mitchell; Agić, Željko. - : Universal Dependencies Consortium, 2018
BASE
Show details
19
Do FreeWord Order Languages Need More Treebank Data? Investigating Dative Alternation in German, English, and Russian
Gilmanov, Timur [Verfasser]; Abo Mokh, Noor [Verfasser]; Kim, Evgeny [Verfasser]. - Mannheim : Institut für Deutsche Sprache, Bibliothek, 2017
DNB Subject Category Language
Show details
20
Universal Dependencies 2.1
In: https://hal.inria.fr/hal-01682188 ; 2017 (2017)
BASE
Show details

Page: 1 2

Catalogues
0
0
0
0
1
0
0
Bibliographies
0
0
0
0
0
0
0
0
0
Linked Open Data catalogues
0
Online resources
1
0
0
0
Open access documents
34
0
0
0
0
© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern