Page: 1 2 3 4 5 6 7 8 9... 1.020
82 |
Acoustic features of dysphonic speech vs normal speech in New Zealand English speakers
|
|
|
|
BASE
|
|
Show details
|
|
83 |
Modeling verb valency in a computational grammar for Portuguese in the HPSG formalism ; Modelação da valência verbal numa gramática computacional do português no formalismo HPSG
|
|
|
|
In: Domínios de Lingu@gem; Ahead of Print; 1-63 ; 1980-5799 (2022)
|
|
BASE
|
|
Show details
|
|
84 |
Causal and Semantic Relations in L2 Text Processing: An Eye-Tracking Study
|
|
Nahatame, Shingo. - : University of Hawaii National Foreign Language Resource Center, 2022. : Center for Language & Technology, 2022
|
|
BASE
|
|
Show details
|
|
85 |
Recognition of Urdu sign language: a systematic review of the machine learning classification
|
|
|
|
In: PeerJ Comput Sci (2022)
|
|
BASE
|
|
Show details
|
|
86 |
Multi-label emotion classification of Urdu tweets
|
|
|
|
In: PeerJ Comput Sci (2022)
|
|
BASE
|
|
Show details
|
|
87 |
Eine agentenbasierte Architektur für Programmierung mit gesprochener Sprache
|
|
|
|
BASE
|
|
Show details
|
|
88 |
Word Frequency Analysis of Community Reaction to Religious Violence on Social Media
|
|
|
|
In: School of Computer Science & Engineering Faculty Publications (2022)
|
|
BASE
|
|
Show details
|
|
89 |
(Re)shaping online narratives: when bots promote the message of President Trump during his first impeachment
|
|
|
|
In: PeerJ Comput Sci (2022)
|
|
BASE
|
|
Show details
|
|
90 |
A systematic literature review on spam content detection and classification
|
|
|
|
In: PeerJ Comput Sci (2022)
|
|
BASE
|
|
Show details
|
|
91 |
People’s expectations and experiences of big data collection in the Saudi context
|
|
|
|
In: PeerJ Comput Sci (2022)
|
|
BASE
|
|
Show details
|
|
92 |
Developing and evaluating cybersecurity competencies for students in computing programs
|
|
|
|
In: PeerJ Comput Sci (2022)
|
|
BASE
|
|
Show details
|
|
93 |
Multitask Pointer Network for Multi-Representational Parsing
|
|
|
|
Abstract:
Financiado para publicación en acceso aberto: Universidade da Coruña/CISUG ; [Abstract] Dependency and constituent trees are widely used by many artificial intelligence applications for representing the syntactic structure of human languages. Typically, these structures are separately produced by either dependency or constituent parsers. In this article, we propose a transition-based approach that, by training a single model, can efficiently parse any input sentence with both constituent and dependency trees, supporting both continuous/projective and discontinuous/non-projective syntactic structures. To that end, we develop a Pointer Network architecture with two separate task-specific decoders and a common encoder, and follow a multitask learning strategy to jointly train them. The resulting quadratic system, not only becomes the first parser that can jointly produce both unrestricted constituent and dependency trees from a single model, but also proves that both syntactic formalisms can benefit from each other during training, achieving state-of-the-art accuracies in several widely-used benchmarks such as the continuous English and Chinese Penn Treebanks, as well as the discontinuous German NEGRA and TIGER datasets. ; We acknowledge the European Research Council (ERC), which has funded this research under the European Union’s Horizon 2020 research and innovation programme (FASTPARSE, grant agreement No 714150), ERDF/MICINN-AEI (ANSWER-ASAP, TIN2017-85160-C2-1-R; SCANNER-UDC, PID2020-113230RB-C21), Xunta de Galicia, Spain (ED431C 2020/11), and Centro de Investigación de Galicia “CITIC”, funded by Xunta de Galicia, Spain and the European Union (ERDF - Galicia 2014–2020 Program), by grant ED431G 2019/01. Funding for open access charge: Universidade da Coruña / CISUG ; Xunta de Galicia; ED431C 2020/11 ; Xunta de Galicia; ED431G 2019/01
|
|
Keyword:
Computational linguistics; Constituent parsing; Deep learning; Dependency parsing; Natural language processing; Neural network; Parsing
|
|
URL: https://doi.org/10.1016/j.knosys.2021.107760 http://hdl.handle.net/2183/29887
|
|
BASE
|
|
Hide details
|
|
94 |
CorpusExplorer ; Eine Software zur korpuspragmatischen Analyse
|
|
|
|
BASE
|
|
Show details
|
|
95 |
Horse or pony? Visual Typicality and Lexical Frequency Affect Variability in Object Naming
|
|
|
|
In: Proceedings of the Society for Computation in Linguistics (2022)
|
|
BASE
|
|
Show details
|
|
96 |
Masked language models directly encode linguistic uncertainty
|
|
|
|
In: Proceedings of the Society for Computation in Linguistics (2022)
|
|
BASE
|
|
Show details
|
|
97 |
Learning Stress Patterns with a Sequence-to-Sequence Neural Network
|
|
|
|
In: Proceedings of the Society for Computation in Linguistics (2022)
|
|
BASE
|
|
Show details
|
|
98 |
Modeling human-like morphological prediction
|
|
|
|
In: Proceedings of the Society for Computation in Linguistics (2022)
|
|
BASE
|
|
Show details
|
|
99 |
The interaction between cognitive ease and informativeness shapes the lexicons of natural languages
|
|
|
|
In: Proceedings of the Society for Computation in Linguistics (2022)
|
|
BASE
|
|
Show details
|
|
100 |
What is so Plautine about Plautine Language? Computers and the Style of Early Latin Drama
|
|
|
|
In: Peter Barrios-Lech (2022)
|
|
BASE
|
|
Show details
|
|
Page: 1 2 3 4 5 6 7 8 9... 1.020
|
|