Massive choice, ample tasks (MaChAmp): A toolkit for multi-task learning in NLP
Transfer learning, particularly approaches that combine multi-task learning with pre-trained
contextualized embeddings and fine-tuning, have advanced the field of Natural Language …
contextualized embeddings and fine-tuning, have advanced the field of Natural Language …
Spoken language treebanks in Universal Dependencies: An overview
K Dobrovoljc - … of the Thirteenth Language Resources and …, 2022 - aclanthology.org
Given the benefits of syntactically annotated collections of transcribed speech in spoken
language research and applications, many spoken language treebanks have been …
language research and applications, many spoken language treebanks have been …
Two languages, one treebank: building a Turkish–German code-switching treebank and its challenges
Ö Çetinoğlu, Ç Çöltekin - Language Resources and Evaluation, 2023 - Springer
This paper presents the SAGT Turkish–German code-switching treebank, and observations
and annotation challenges we encountered during its development. The treebank consists …
and annotation challenges we encountered during its development. The treebank consists …
Experimental standards for deep learning in natural language processing research
The field of Deep Learning (DL) has undergone explosive growth during the last decade,
with a substantial impact on Natural Language Processing (NLP) as well. Yet, compared to …
with a substantial impact on Natural Language Processing (NLP) as well. Yet, compared to …
Annotation guidelines of UD and SUD treebanks for spoken corpora
S Kahane, B Caron, E Strickland… - Proceedings of the 20th …, 2021 - hal.parisnanterre.fr
This paper presents practical and theoretical guidelines for the development of treebanks for
spoken languages in the UD and SUD annotation schemes. We discuss text-sound …
spoken languages in the UD and SUD annotation schemes. We discuss text-sound …
UD_Japanese-CEJC: Dependency Relation Annotation on Corpus of Everyday Japanese Conversation
In this study, we have developed Universal Dependencies (UD) resources for spoken
Japanese in the Corpus of Everyday Japanese Conversation (CEJC). The CEJC is a large …
Japanese in the Corpus of Everyday Japanese Conversation (CEJC). The CEJC is a large …
Data-driven Parsing Evaluation for Child-Parent Interactions
Z Liu, E Prud'hommeaux - Transactions of the Association for …, 2023 - direct.mit.edu
We present a syntactic dependency treebank for naturalistic child and child-directed spoken
English. Our annotations largely follow the guidelines of the Universal Dependencies project …
English. Our annotations largely follow the guidelines of the Universal Dependencies project …
Improving Code-Switching Dependency Parsing with Semi-Supervised Auxiliary Tasks
Code-switching dependency parsing stands as a challenging task due to both the scarcity of
necessary resources and the structural difficulties embedded in code-switched languages …
necessary resources and the structural difficulties embedded in code-switched languages …
Cross-Lingual and Genre-Supervised Parsing and Tagging for Low-Resource Spoken Data
I Fosteri - 2023 - diva-portal.org
Dealing with low-resource languages is a challenging task, because of the absence of
sufficient data to train machine-learning models to make predictions on these languages …
sufficient data to train machine-learning models to make predictions on these languages …
[PDF][PDF] Universal Dependencies and Language Contact Annotation: Experience from Warao refugees signs in Brazil
D Buzato - Proceedings of the 2nd Edition of the Universal …, 2023 - aclanthology.org
This article aims to present a work in progress that proposes to describe, from the Universal
Dependencies (UD) project, the linguistic contact between the Warao language …
Dependencies (UD) project, the linguistic contact between the Warao language …