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)
|
|
Abstract:
International audience ; Automatic detection of abusive online content such as hate speech, offensive language, threats, etc. has become prevalent in social media, with multiple efforts dedicated to detecting this phenomenon in English. However, detecting hatred and abuse in low-resource languages is a non-trivial challenge. The lack of sufficient labeled data in low-resource languages and inconsistent generalization ability of transformer-based multilingual pre-trained language models for typologically diverse languages make these models inefficient in some cases. We propose a meta learning-based approach to study the problem of few-shot hate speech and offensive language detection in low-resource languages that will allow hateful or offensive content to be predicted by only observing a few labeled data items in a specific target language. We investigate the feasibility of applying a meta learning approach in cross-lingual few-shot hate speech detection by leveraging two meta learning models based on optimization-based and metric-based (MAML and Proto-MAML) methods. To the best of our knowledge, this is the first effort of this kind. To evaluate the performance of our approach, we consider hate speech and offensive language detection as two separate tasks and make two diverse collections of different publicly available datasets comprising 15 datasets across 8 languages for hate speech and 6 datasets across 6 languages for offensive language. Our experiments show that meta learning-based models outperform transfer learning-based models in a majority of cases, and that Proto-MAML is the best performing model, as it can quickly generalize and adapt to new languages with only a few labeled data points (generally, 16 samples per class yields an effective performance) to identify hateful or offensive content.
|
|
Keyword:
[INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI]; [INFO.INFO-NI]Computer Science [cs]/Networking and Internet Architecture [cs.NI]; [INFO.INFO-SI]Computer Science [cs]/Social and Information Networks [cs.SI]; Cross-lingual classification; Few-shot learning; Hate speech; Meta learning; Offensive language; Transfer learning; XLMRoBERTa
|
|
URL: https://doi.org/10.1109/ACCESS.2022.3147588 https://hal.archives-ouvertes.fr/hal-03559484
|
|
BASE
|
|
Hide details
|
|
2 |
FAIRsharing record for: General Ontology for Linguistic Description ... : GOLD ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
Unsupervised quantification of entity consistency between photos and text in real-world news ...
|
|
Müller-Budack, Eric. - : Hannover : Institutionelles Repositorium der Leibniz Universität Hannover, 2022
|
|
BASE
|
|
Show details
|
|
5 |
EMBEDDIA tools output example corpus of Estonian, Croatian and Latvian news articles 1.0
|
|
|
|
BASE
|
|
Show details
|
|
6 |
О ЛЕКСИКО-ГРАММАТИЧЕСКИХ РАЗРЯДАХ ИМЕН СУЩЕСТВИТЕЛЬНЫХ В ТАБАСАРАНСКОМ ЯЗЫКЕ ... : ABOUT LEXICAL AND GRAMMATICAL CATEGORIES OF NOUNS IN THE TABASARAN LANGUAGE ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
Mining an English-Chinese parallel Dataset of Financial News
|
|
|
|
In: Journal of Open Humanities Data; Vol 8 (2022); 9 ; 2059-481X (2022)
|
|
BASE
|
|
Show details
|
|
9 |
Discriminating Bacterial Infection from Other Causes of Fever Using Body Temperature Entropy Analysis
|
|
|
|
In: Entropy; Volume 24; Issue 4; Pages: 510 (2022)
|
|
BASE
|
|
Show details
|
|
11 |
The Multilingual Pragmatics of New Englishes: An Analysis of Question Tags in Nigerian English
|
|
|
|
BASE
|
|
Show details
|
|
12 |
The phonetics and phonology of Hong Kong English: a study of fricatives
|
|
|
|
BASE
|
|
Show details
|
|
13 |
Code: Drift in a Popular Metal Oxide Sensor Dataset Reveals Limitations for Gas Classification Benchmarks ...
|
|
|
|
BASE
|
|
Show details
|
|
14 |
Code: Drift in a Popular Metal Oxide Sensor Dataset Reveals Limitations for Gas Classification Benchmarks ...
|
|
|
|
BASE
|
|
Show details
|
|
15 |
Addressing multilingualism in the GoTriple discovery platform ...
|
|
|
|
BASE
|
|
Show details
|
|
16 |
Addressing multilingualism in the GoTriple discovery platform ...
|
|
|
|
BASE
|
|
Show details
|
|
17 |
The Terms of “You(s)”: How the Term of Address Used by Conversational Agents Influences User Evaluations in French and German Linguaculture ...
|
|
|
|
BASE
|
|
Show details
|
|
18 |
'Muscles of mussels' and 'hooks of bananas' - the (incipient) numeral classifier system of Ugare (Tivoid, Cameroon/Nigeria) ...
|
|
|
|
BASE
|
|
Show details
|
|
19 |
Towards reconstructing a Proto-Tivoid numeral classifier system ...
|
|
|
|
BASE
|
|
Show details
|
|
20 |
Measuring Semantic Similarity of Documents by Using Named Entity Recognition Methods
|
|
|
|
In: Masters (2022)
|
|
BASE
|
|
Show details
|
|
|
|