1 |
Cross-lingual few-shot hate speech and offensive language detection using meta learning
|
|
|
|
In: ISSN: 2169-3536 ; EISSN: 2169-3536 ; IEEE Access ; https://hal.archives-ouvertes.fr/hal-03559484 ; IEEE Access, IEEE, 2022, 10, pp.14880-14896. ⟨10.1109/ACCESS.2022.3147588⟩ (2022)
|
|
BASE
|
|
Show details
|
|
2 |
Measuring Terminology Consistency in Translated Corpora: Implementation of the Herfindahl-Hirshman Index
|
|
|
|
In: Information; Volume 13; Issue 2; Pages: 43 (2022)
|
|
BASE
|
|
Show details
|
|
3 |
ETHNOCULTURAL AND SOCIOLINGUISTIC FACTORS IN TEACHING RUSSIAN AS A FOREIGN LANGUAGE ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
Neural-based Knowledge Transfer in Natural Language Processing
|
|
|
|
BASE
|
|
Show details
|
|
5 |
Science research writing: for native and non-native speakers of English
|
|
|
|
BASE
|
|
Show details
|
|
6 |
Hate speech and offensive language detection using transfer learning approaches ; Détection du discours de haine et du langage offensant utilisant des approches de Transfer Learning
|
|
|
|
In: https://tel.archives-ouvertes.fr/tel-03276023 ; Document and Text Processing. Institut Polytechnique de Paris, 2021. English. ⟨NNT : 2021IPPAS007⟩ (2021)
|
|
BASE
|
|
Show details
|
|
7 |
Improving Multilingual Models for the Swedish Language : Exploring CrossLingual Transferability and Stereotypical Biases
|
|
|
|
Abstract:
The best performing Transformer-based Language Models are monolingual and mainly focus on high-resource languages such as English. In an attempt to extend their usage to more languages, multilingual models have been introduced. Nevertheless, multilingual models still underperform on a specific language when compared to a similarly sized monolingual model that has been trained solely on that specific language. The main objective of this thesis project is to explore how a multilingual model can be improved for Swedish which is a low-resource language. We study if a multilingual model can benefit from further pre-training on Swedish or on a mix of English and Swedish text before fine-tuning. Our results on the task of semantic text similarity show that further pre-training increases the Pearson Correlation Score by 5% for specific cross-lingual language settings. Taking into account the responsibilities that arise from the increased use of Language Models in real-world applications, we supplement our work by additional experiments that measure stereotypical biases associated to gender. We use a new dataset that we designed specifically for that purpose. Our systematic study compares Swedish to English as well as various model sizes. The insights from our exploration indicate that the Swedish language carries less bias associated to gender than English and that higher manifestation of gender bias is associated to the use of larger Language Models. ; De bästa Transformerbaserade språkmodellerna är enspråkiga och fokuserar främst på resursrika språk som engelska. I ett försök att utöka deras användning till fler språk har flerspråkiga modeller introducerats. Flerspråkiga modeller underpresterar dock fortfarande på enskilda språk när man jämför med en enspråkig modell av samma storlek som enbart har tränats på det specifika språket. Huvudsyftet med detta examensarbete är att utforska hur en flerspråkig modell kan förbättras för svenska som är ett resurssnålt språk. Vi studerar om en flerspråkig modell kan dra nytta av ytterligare förträning på svenska eller av en blandning av engelsk och svensk text innan finjustering. Våra resultat på uppgiften om semantisk textlikhet visar att ytterligare förträning ökar Pearsons korrelationspoäng med 5% för specifika tvärspråkiga språkinställningar. Med hänsyn till det ansvar som uppstår från den ökade användningen av språkmodeller i verkliga tillämpningar, kompletterar vi vårt arbete med ytterligare experiment som mäter stereotypa fördomar kopplade till kön. Vi använder en ny datauppsättning som vi har utformat specifikt för det ändamålet. Vår systematiska studie jämför svenska med engelska samt olika modellstorlekar. Insikterna från vår forskning tyder på att det svenska språket har mindre partiskhet förknippat med kön än engelska, samt att högre manifestation av könsfördomar är förknippat med användningen av större språkmodeller.
|
|
Keyword:
Computer and Information Sciences; Cross-Lingual Transfer; Data- och informationsvetenskap; Deep Learning; Multilingual Models; Natural Language Processing; Stereotypical Biases; Transformers
|
|
URL: http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-305920
|
|
BASE
|
|
Hide details
|
|
8 |
Europe, l'autre cap, entre traductions et transferts
|
|
|
|
In: https://hal.archives-ouvertes.fr/hal-03124335 ; 2020 (2020)
|
|
BASE
|
|
Show details
|
|
9 |
Clickbait detection using multimodel fusion and transfer learning ; Détection de clickbait utilisant fusion multimodale et apprentissage par transfert
|
|
|
|
In: https://tel.archives-ouvertes.fr/tel-03139880 ; Social and Information Networks [cs.SI]. Institut Polytechnique de Paris, 2020. English. ⟨NNT : 2020IPPAS025⟩ (2020)
|
|
BASE
|
|
Show details
|
|
10 |
Interpretation of Swedish Sign Language using Convolutional Neural Networks and Transfer Learning
|
|
|
|
BASE
|
|
Show details
|
|
11 |
Comments on the book "Architects of Intelligence" by Martin Ford in the light of the SP Theory of Intelligence
|
|
|
|
In: https://hal.archives-ouvertes.fr/hal-02061171 ; 2019 (2019)
|
|
BASE
|
|
Show details
|
|
12 |
The dialectical meaning of offshored work: neoliberal desires and labour arbitrage in post-socialist Romania
|
|
|
|
BASE
|
|
Show details
|
|
13 |
Theory and approaches of group decision making with uncertain linguistic expressions
|
|
|
|
BASE
|
|
Show details
|
|
14 |
Terminology acquisition methods in Arabic : Application in the medical domain ; Méthodes d'acquisition terminologique en arabe : Application au domaine médical
|
|
|
|
In: https://tel.archives-ouvertes.fr/tel-02326714 ; Informatique et langage [cs.CL]. Université Paris Saclay (COmUE); Université de Sfax (Tunisie). Faculté des Sciences économiques et de gestion, 2019. Français. ⟨NNT : 2019SACLS085⟩ (2019)
|
|
BASE
|
|
Show details
|
|
15 |
Neural Methods Towards Concept Discovery from Text via Knowledge Transfer
|
|
|
|
In: http://rave.ohiolink.edu/etdc/view?acc_num=osu1572387318988274 (2019)
|
|
BASE
|
|
Show details
|
|
16 |
Perceptual attention as the locus of transfer to nonnative speech perception
|
|
|
|
BASE
|
|
Show details
|
|
17 |
Business Perspectives of Philosophy and Knowledge: Occident Contra Islam
|
|
|
|
BASE
|
|
Show details
|
|
18 |
Communicating science: a practical guide for engineers and physical scientists
|
|
|
|
BASE
|
|
Show details
|
|
19 |
Data-driven problem-solving in international business communication: examining the use of bilingual web-based tools for text production with advanced English as a foreign language professionals
|
|
|
|
BASE
|
|
Show details
|
|
|
|