Home
Catalogue search
Refine your search:
Keyword:
Computation and Language cs.CL (41)
FOS Computer and information sciences (41)
ddc:410 (25)
Deutsch (24)
ddc:000 (24)
Wissenschaftsgeschichte (20. Jahrhundert) (18)
440.romance.languages (17)
400.philology (16)
Review (12)
Sprache, Linguistik (12)
more
Creator / Publisher:
Schütze, Hinrich (121)
The Pennsylvania State University CiteSeerX Archives (62)
Hinrich Schütze (56)
Ehlers, Klaas-Hinrich (51)
Dufter, Philipp (31)
Hudde, Hinrich (23)
Michael Walsh (11)
Zhao, Mengjie (11)
Roth, Klaus-Hinrich (10)
Hofmann, Valentin (9)
more
Year
Medium
Type
BLLDB-Access
Search in the Catalogues and Directories
All fields
Title
Creator / Publisher
Keyword
Year
AND
OR
AND NOT
All fields
Title
Creator / Publisher
Keyword
Year
AND
OR
AND NOT
All fields
Title
Creator / Publisher
Keyword
Year
AND
OR
AND NOT
All fields
Title
Creator / Publisher
Keyword
Year
AND
OR
AND NOT
All fields
Title
Creator / Publisher
Keyword
Year
Sort by
creator [A → Z]
'
creator [Z → A]
'
publishing year ↑ (asc)
'
publishing year ↓ (desc)
'
title [A → Z]
'
title [Z → A]
'
Simple Search
Page:
1
2
3
4
5
...
18
Hits 1 – 20 of 360
1
Graph Neural Networks for Multiparallel Word Alignment ...
Imani, Ayyoob
;
Şenel, Lütfi Kerem
;
Sabet, Masoud Jalili
. - : arXiv, 2022
BASE
Show details
2
CaMEL: Case Marker Extraction without Labels ...
Weissweiler, Leonie
;
Hofmann, Valentin
;
Sabet, Masoud Jalili
. - : arXiv, 2022
BASE
Show details
3
Listening to Affected Communities to Define Extreme Speech: Dataset and Experiments ...
Maronikolakis, Antonis
;
Wisiorek, Axel
;
Nann, Leah
. - : arXiv, 2022
BASE
Show details
4
Differentiable Multi-Agent Actor-Critic for Multi-Step Radiology Report Summarization ...
Karn, Sanjeev Kumar
;
Liu, Ning
;
Schuetze, Hinrich
. - : arXiv, 2022
BASE
Show details
5
Geographic Adaptation of Pretrained Language Models ...
Hofmann, Valentin
;
Glavaš, Goran
;
Ljubešić, Nikola
. - : arXiv, 2022
BASE
Show details
6
Distributed representations for multilingual language processing
Dufter, Philipp
[Verfasser];
Schütze, Hinrich
[Akademischer Betreuer]. - München : Universitätsbibliothek der Ludwig-Maximilians-Universität, 2021
DNB Subject Category Language
Show details
7
Domain adaptation in Natural Language Processing
Sedinkina, Marina
[Verfasser];
Schütze, Hinrich
[Akademischer Betreuer]. - München : Universitätsbibliothek der Ludwig-Maximilians-Universität, 2021
DNB Subject Category Language
Show details
8
Combining contextualized and non-contextualized embeddings for domain adaptation and beyond
Pörner, Nina Mareike
[Verfasser];
Schütze, Hinrich
[Akademischer Betreuer]. - München : Universitätsbibliothek der Ludwig-Maximilians-Universität, 2021
DNB Subject Category Language
Show details
9
Graph Algorithms for Multiparallel Word Alignment
Imani, Ayyoob
;
Sabet, Masoud,
;
Keremşenel, Lütfi
...
In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing ; The 2021 Conference on Empirical Methods in Natural Language Processing ; https://hal.archives-ouvertes.fr/hal-03424044 ; The 2021 Conference on Empirical Methods in Natural Language Processing, Association for Computational Linguistics, Nov 2021, Punta Cana, Dominica ; https://2021.emnlp.org/ (2021)
BASE
Show details
10
Static Embeddings as Efficient Knowledge Bases? ...
Dufter, Philipp
;
Kassner, Nora
;
Schütze, Hinrich
. - : arXiv, 2021
BASE
Show details
11
Does He Wink or Does He Nod? A Challenging Benchmark for Evaluating Word Understanding of Language Models ...
Senel, Lutfi Kerem
;
Schütze, Hinrich
. - : arXiv, 2021
BASE
Show details
12
Superbizarre Is Not Superb: Derivational Morphology Improves BERT's Interpretation of Complex Words ...
The Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing 2021
;
., Hinrich
;
Hofmann, Valentin
. - : Underline Science Inc., 2021
BASE
Show details
13
Discrete and Soft Prompting for Multilingual Models ...
Zhao, Mengjie
;
Schütze, Hinrich
. - : arXiv, 2021
BASE
Show details
14
ParCourE: A Parallel Corpus Explorer for a Massively Multilingual Corpus ...
Imani, Ayyoob
;
Sabet, Masoud Jalili
;
Dufter, Philipp
. - : arXiv, 2021
BASE
Show details
15
Multilingual LAMA: Investigating Knowledge in Multilingual Pretrained Language Models ...
Kassner, Nora
;
Dufter, Philipp
;
Schütze, Hinrich
. - : arXiv, 2021
BASE
Show details
16
Wine is Not v i n. -- On the Compatibility of Tokenizations Across Languages ...
Maronikolakis, Antonis
;
Dufter, Philipp
;
Schütze, Hinrich
. - : arXiv, 2021
BASE
Show details
17
Graph Algorithms for Multiparallel Word Alignment ...
Imani, Ayyoob
;
Sabet, Masoud Jalili
;
Şenel, Lütfi Kerem
. - : arXiv, 2021
BASE
Show details
18
Locating Language-Specific Information in Contextualized Embeddings ...
Liang, Sheng
;
Dufter, Philipp
;
Schütze, Hinrich
. - : arXiv, 2021
BASE
Show details
19
Dynamic Contextualized Word Embeddings ...
The Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing 2021
;
., Hinrich
;
Hofmann, Valentin
. - : Underline Science Inc., 2021
BASE
Show details
20
Measuring and Improving Consistency in Pretrained Language Models ...
The 2021 Conference on Empirical Methods in Natural Language Processing 2021
;
Elazar, Yanai
;
Goldberg, Yoav
;
Hovy, Eduard
;
Kassner, Nora
;
Ravfogel, Shauli
;
Ravichander, Abhilasha
;
Schütze, Hinrich
. - : Underline Science Inc., 2021
Abstract:
Consistency of a model — that is, the invariance of its behavior under meaning preserving alternations in its input — is a highly desirable property in natural language processing. In this paper we study the question: Are Pretrained Language Models (PLMs) consistent with respect to factual knowledge? To this end, we create PARAREL , a high-quality resource of cloze-style query English paraphrases. It contains a total of 328 paraphrases for 38 relations. Using PARAREL , we show that the consistency of all PLMs we experiment with is poor – though with high variance between relations. Our analysis of the representational spaces of PLMs suggests that they have a poor structure and are currently not suitable for representing knowledge robustly. Finally, we propose a method for improving model consistency and experimentally demonstrate its effectiveness. ...
Keyword:
Computational Linguistics
;
Language Models
;
Machine Learning
;
Machine Learning and Data Mining
;
Natural Language Processing
URL:
https://underline.io/lecture/38196-measuring-and-improving-consistency-in-pretrained-language-models
https://dx.doi.org/10.48448/rb2w-8959
BASE
Hide details
Page:
1
2
3
4
5
...
18
Mobile view
All
Catalogues
UB Frankfurt Linguistik
19
IDS Mannheim
21
OLC Linguistik
23
UB Frankfurt Retrokatalog
0
DNB Subject Category Language
25
Institut für Empirische Sprachwissenschaft
1
Leibniz-Centre General Linguistics (ZAS)
6
Bibliographies
BLLDB
55
BDSL
2
IDS Bibliografie zur deutschen Grammatik
3
IDS Bibliografie zur Gesprächsforschung
2
IDS Konnektoren im Deutschen
1
IDS Präpositionen im Deutschen
0
IDS OBELEX meta
0
MPI-SHH Linguistics Collection
0
MPI for Psycholinguistics
9
Linked Open Data catalogues
Annohub
0
Online resources
Link directory
1
Journal directory
0
Database directory
0
Dictionary directory
0
Open access documents
BASE
218
Linguistik-Repository
0
IDS Publikationsserver
1
Online dissertations
2
Language Description Heritage
0
© 2013 - 2024 Lin|gu|is|tik
|
Imprint
|
Privacy Policy
|
Datenschutzeinstellungen ändern