Domain Classification-based Source-specific Term Penalization for Domain
Adaptation in Hate-speech Detection
- URL: http://arxiv.org/abs/2209.08681v1
- Date: Sun, 18 Sep 2022 23:52:22 GMT
- Title: Domain Classification-based Source-specific Term Penalization for Domain
Adaptation in Hate-speech Detection
- Authors: Tulika Bose, Nikolaos Aletras, Irina Illina, Dominique Fohr
- Abstract summary: State-of-the-art approaches for hate-speech detection exhibit poor performance in out-of-domain settings.
We propose a domain adaptation approach that automatically extracts and penalizes source-specific terms.
- Score: 30.462596705180534
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: State-of-the-art approaches for hate-speech detection usually exhibit poor
performance in out-of-domain settings. This occurs, typically, due to
classifiers overemphasizing source-specific information that negatively impacts
its domain invariance. Prior work has attempted to penalize terms related to
hate-speech from manually curated lists using feature attribution methods,
which quantify the importance assigned to input terms by the classifier when
making a prediction. We, instead, propose a domain adaptation approach that
automatically extracts and penalizes source-specific terms using a domain
classifier, which learns to differentiate between domains, and
feature-attribution scores for hate-speech classes, yielding consistent
improvements in cross-domain evaluation.
Related papers
- Task-specific Inconsistency Alignment for Domain Adaptive Object
Detection [38.027790951157705]
Detectors trained with massive labeled data often exhibit dramatic performance degradation in certain scenarios with data distribution gap.
We propose Task-specific Inconsistency Alignment (TIA), by developing a new alignment mechanism in separate task spaces.
TIA demonstrates superior results on various scenarios to the previous state-of-the-art methods.
arXiv Detail & Related papers (2022-03-29T08:36:33Z) - Domain-Class Correlation Decomposition for Generalizable Person
Re-Identification [34.813965300584776]
In person re-identification, the domain and class are correlated.
We show that domain adversarial learning will lose certain information about class due to this domain-class correlation.
Our model outperforms the state-of-the-art methods on the large-scale domain generalization Re-ID benchmark.
arXiv Detail & Related papers (2021-06-29T09:45:03Z) - ToAlign: Task-oriented Alignment for Unsupervised Domain Adaptation [84.90801699807426]
We study what features should be aligned across domains and propose to make the domain alignment proactively serve classification.
We explicitly decompose a feature in the source domain intoa task-related/discriminative feature that should be aligned, and a task-irrelevant feature that should be avoided/ignored.
arXiv Detail & Related papers (2021-06-21T02:17:48Z) - Instance Level Affinity-Based Transfer for Unsupervised Domain
Adaptation [74.71931918541748]
We propose an instance affinity based criterion for source to target transfer during adaptation, called ILA-DA.
We first propose a reliable and efficient method to extract similar and dissimilar samples across source and target, and utilize a multi-sample contrastive loss to drive the domain alignment process.
We verify the effectiveness of ILA-DA by observing consistent improvements in accuracy over popular domain adaptation approaches on a variety of benchmark datasets.
arXiv Detail & Related papers (2021-04-03T01:33:14Z) - Re-energizing Domain Discriminator with Sample Relabeling for
Adversarial Domain Adaptation [88.86865069583149]
Unsupervised domain adaptation (UDA) methods exploit domain adversarial training to align the features to reduce domain gap.
In this work, we propose an efficient optimization strategy named Re-enforceable Adversarial Domain Adaptation (RADA)
RADA aims to re-energize the domain discriminator during the training by using dynamic domain labels.
arXiv Detail & Related papers (2021-03-22T08:32:55Z) - Interventional Domain Adaptation [81.0692660794765]
Domain adaptation (DA) aims to transfer discriminative features learned from source domain to target domain.
Standard domain-invariance learning suffers from spurious correlations and incorrectly transfers the source-specifics.
We create counterfactual features that distinguish the domain-specifics from domain-sharable part.
arXiv Detail & Related papers (2020-11-07T09:53:13Z) - Domain Adversarial Fine-Tuning as an Effective Regularizer [80.14528207465412]
In Natural Language Processing (NLP), pretrained language models (LMs) that are transferred to downstream tasks have been recently shown to achieve state-of-the-art results.
Standard fine-tuning can degrade the general-domain representations captured during pretraining.
We introduce a new regularization technique, AFTER; domain Adversarial Fine-Tuning as an Effective Regularizer.
arXiv Detail & Related papers (2020-09-28T14:35:06Z) - Improving Domain-Adapted Sentiment Classification by Deep Adversarial
Mutual Learning [51.742040588834996]
Domain-adapted sentiment classification refers to training on a labeled source domain to well infer document-level sentiment on an unlabeled target domain.
We propose a novel deep adversarial mutual learning approach involving two groups of feature extractors, domain discriminators, sentiment classifiers, and label probers.
arXiv Detail & Related papers (2020-02-01T01:22:44Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.