DE eng

Search in the Catalogues and Directories

Page: 1 2 3 4 5
Hits 1 – 20 of 89

1
One Country, 700+ Languages: NLP Challenges for Underrepresented Languages and Dialects in Indonesia ...
BASE
Show details
2
Universals of Linguistic Idiosyncrasy in Multilingual Computational Linguistics ; Universals of Linguistic Idiosyncrasy in Multilingual Computational Linguistics: Dagstuhl Seminar 21351
In: Universals of Linguistic Idiosyncrasy in Multilingual Computational Linguistics ; https://hal.archives-ouvertes.fr/hal-03507948 ; Universals of Linguistic Idiosyncrasy in Multilingual Computational Linguistics, Aug 2021, pp.89--138, 2021, 2192-5283. ⟨10.4230/DagRep.11.7.89⟩ ; https://gitlab.com/unlid/dagstuhl-seminar/-/wikis/home (2021)
BASE
Show details
3
Universals of Linguistic Idiosyncrasy in Multilingual Computational Linguistics (Dagstuhl Seminar 21351)
Croft, William; Savary, Agata; Baldwin, Timothy. - : Dagstuhl Reports. DagRep, Volume 11, Issue 7, 2021
BASE
Show details
4
Evaluating the Efficacy of Summarization Evaluation across Languages ...
BASE
Show details
5
Fairness-aware Class Imbalanced Learning ...
BASE
Show details
6
Just What do You Think You're Doing, Dave?' A Checklist for Responsible Data Use in NLP ...
BASE
Show details
7
Decoupling Adversarial Training for Fair NLP ...
BASE
Show details
8
IndoBERTweet: A Pretrained Language Model for Indonesian Twitter with Effective Domain-Specific Vocabulary Initialization ...
BASE
Show details
9
Evaluating the Efficacy of Summarization Evaluation across Languages ...
BASE
Show details
10
Universals of Linguistic Idiosyncrasy in Multilingual Computational Linguistics (Dagstuhl Seminar 21351) ...
Baldwin, Timothy; Croft, William; Nivre, Joakim; Savary, Agata. - : Schloss Dagstuhl - Leibniz-Zentrum für Informatik, 2021
Abstract: Computational linguistics builds models that can usefully process and produce language and that can increase our understanding of linguistic phenomena. From the computational perspective, language data are particularly challenging notably due to their variable degree of idiosyncrasy (unexpected properties shared by few peer objects), and the pervasiveness of non-compositional phenomena such as multiword expressions (whose meaning cannot be straightforwardly deduced from the meanings of their components, e.g. red tape, by and large, to pay a visit and to pull one’s leg) and constructions (conventional associations of forms and meanings). Additionally, if models and methods are to be consistent and valid across languages, they have to face specificities inherent either to particular languages, or to various linguistic traditions. These challenges were addressed by the Dagstuhl Seminar 21351 entitled "Universals of Linguistic Idiosyncrasy in Multilingual Computational Linguistics", which took place on 30-31 ... : DagRep, Volume 11, Issue 7, pages 89-138 ...
Keyword: computational linguistics; Computing methodologies → Artificial intelligence; idiosyncrasy; language universals; morphosyntax; multiword expressions
URL: https://drops.dagstuhl.de/opus/volltexte/2021/15591/
https://dx.doi.org/10.4230/dagrep.11.7.89
BASE
Hide details
11
Learning Contextualised Cross-lingual Word Embeddings and Alignments for Extremely Low-Resource Languages Using Parallel Corpora ...
BASE
Show details
12
Balancing out Bias: Achieving Fairness Through Training Reweighting ...
BASE
Show details
13
Evaluating Document Coherence Modelling ...
BASE
Show details
14
ChEMU 2020: Natural Language Processing Methods Are Effective for Information Extraction From Chemical Patents
In: Front Res Metr Anal (2021)
BASE
Show details
15
Liputan6: A Large-scale Indonesian Dataset for Text Summarization ...
BASE
Show details
16
WikiUMLS: Aligning UMLS to Wikipedia via Cross-lingual Neural Ranking ...
BASE
Show details
17
Learning Contextualised Cross-lingual Word Embeddings and Alignments for Extremely Low-Resource Languages Using Parallel Corpora ...
BASE
Show details
18
Target Word Masking for Location Metonymy Resolution ...
BASE
Show details
19
Target Word Masking for Location Metonymy Resolution ...
BASE
Show details
20
IndoLEM and IndoBERT: A Benchmark Dataset and Pre-trained Language Model for Indonesian NLP ...
BASE
Show details

Page: 1 2 3 4 5

Catalogues
0
0
5
0
3
0
0
Bibliographies
7
0
0
0
0
0
2
0
1
Linked Open Data catalogues
0
Online resources
0
0
0
0
Open access documents
73
0
0
0
0
© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern