DE eng

Search in the Catalogues and Directories

Hits 1 – 13 of 13

1
Cross-Attention is All You Need: Adapting Pretrained Transformers for Machine Translation ...
BASE
Show details
2
RiddleSense: Reasoning about Riddle Questions Featuring Linguistic Creativity and Commonsense Knowledge ...
BASE
Show details
3
Learning Contextualized Knowledge Structures for Commonsense Reasoning ...
BASE
Show details
4
AdaTag: Multi-Attribute Value Extraction from Product Profiles with Adaptive Decoding ...
BASE
Show details
5
RICA: Evaluating Robust Inference Capabilities Based on Commonsense Axioms ...
BASE
Show details
6
RockNER: A Simple Method to Create Adversarial Examples for Evaluating the Robustness of Named Entity Recognition Models ...
BASE
Show details
7
ECONET: Effective Continual Pretraining of Language Models for Event Temporal Reasoning ...
BASE
Show details
8
Discretized Integrated Gradients for Explaining Language Models ...
BASE
Show details
9
Improving Counterfactual Generation for Fair Hate Speech Detection ...
Abstract: Bias mitigation approaches reduce models' dependence on sensitive features of data, such as social group tokens (SGTs), resulting in equal predictions across the sensitive features. In hate speech detection, however, equalizing model predictions may ignore important differences among targeted social groups, as hate speech can contain stereotypical language specific to each SGT. Here, to take the specific language about each SGT into account, we rely on counterfactual fairness and equalize predictions among counterfactuals, generated by changing the SGTs. Our method evaluates the similarity in sentence likelihoods (via pre-trained language models) among counterfactuals, to treat SGTs equally only within interchangeable contexts. By applying logit pairing to equalize outcomes on the restricted set of counterfactuals for each instance, we improve fairness metrics while preserving model performance on hate speech detection. ...
Keyword: Computational Linguistics; Condensed Matter Physics; Deep Learning; Electromagnetism; FOS Physical sciences; Information and Knowledge Engineering; Neural Network; Semantics
URL: https://dx.doi.org/10.48448/62eb-1334
https://underline.io/lecture/30169-improving-counterfactual-generation-for-fair-hate-speech-detection
BASE
Hide details
10
Learning to Generate Task-Specific Adapters from Task Description ...
BASE
Show details
11
Lawyers are Dishonest? Quantifying Representational Harms in Commonsense Knowledge Resources ...
BASE
Show details
12
Common Sense Beyond English: Evaluating and Improving Multilingual Language Models for Commonsense Reasoning ...
BASE
Show details
13
Extract, Denoise and Enforce: Evaluating and Improving Concept Preservation for Text-to-Text Generation ...
BASE
Show details

Catalogues
0
0
0
0
0
0
0
Bibliographies
0
0
0
0
0
0
0
0
0
Linked Open Data catalogues
0
Online resources
0
0
0
0
Open access documents
13
0
0
0
0
© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern