From english to foreign languages: Transferring pre-trained language models

K Tran - arXiv preprint arXiv:2002.07306, 2020 - arxiv.org
Pre-trained models have demonstrated their effectiveness in many downstream natural
language processing (NLP) tasks. The availability of multilingual pre-trained models …

Memory limitations are hidden in grammar

C Gómez-Rodríguez, MH Christiansen… - arXiv preprint arXiv …, 2019 - arxiv.org
The ability to produce and understand an unlimited number of different sentences is a
hallmark of human language. Linguists have sought to define the essence of this generative …

EXSEQREG: Explaining sequence-based NLP tasks with regions with a case study using morphological features for named entity recognition

O Güngör, T Güngör, S Uskudarli - Plos one, 2020 - journals.plos.org
The state-of-the-art systems for most natural language engineering tasks employ machine
learning methods. Despite the improved performances of these systems, there is a lack of …

[PDF][PDF] Statistical Parser for Urdu

T Ehsan, S Hussain - 2022 - cle.org.pk
ABSTRACT A number of tools for Urdu language processing have been developed in the
past few years to perform word segmentation, part of speech tagging, chunking, named …

Syntax-semantics interactions–seeking evidence from a synchronic analysis of 38 languages

TS Juzek, Y Bizzoni - F1000Research, 2021 - f1000research.com
The notion that, to facilitate processing, as semantic complexity increases, syntactic
complexity decreases, follows from various linguistic theories. This brief report presents the …

Injection of linguistic knowledge into neural text generation models

N Casas Manzanares - 2020 - upcommons.upc.edu
Language is an organic construct. It emanates from the need for communication and
changes through time, influenced by multiple factors. The resulting language structures are …

Distilling Neural Networks for Faster and Greener Dependency Parsing

M Anderson, C Gómez-Rodríguez - openreview.net
The carbon footprint of natural language processing (NLP) research has been increasing in
recent years due to its reliance on large and inefficient neural network implementations …