DE eng

Search in the Catalogues and Directories

Page: 1...4 5 6 7 8 9 10 11 12...236
Hits 141 – 160 of 4.718

141
Investigating Numeracy of a Text-to-Text Transfer model ...
BASE
Show details
142
Raise a Child in Large Language Model: Towards Effective and Generalizable Fine-tuning ...
BASE
Show details
143
On the Cross-lingual Transferability of Contextualized Sense Embeddings ...
BASE
Show details
144
TEET! Tunisian Dataset for Toxic Speech Detection ...
BASE
Show details
145
Towards Automatic Evaluation of Dialog Systems: A Model-Free Off-Policy Evaluation Approach ...
BASE
Show details
146
DMix: Distance Constrained Interpolative Mixup ...
BASE
Show details
147
Revisiting Self-training for Few-shot Learning of Language Model ...
BASE
Show details
148
Can Language Models be Biomedical Knowledge Bases? ...
BASE
Show details
149
Capturing Speaker Incorrectness: Speaker-Focused Post-Correction for Abstractive Dialogue Summarization ...
BASE
Show details
150
BERT-Beta: A Proactive Probabilistic Approach to Text Moderation ...
Abstract: Anthology paper link: https://aclanthology.org/2021.emnlp-main.682/ Abstract: Text moderation for user generated content, which helps to promote healthy interaction among users, has been widely studied and many machine learning models have been proposed. In this work, we explore an alternative perspective by augmenting reactive reviews with proactive forecasting. Specifically, we propose a new concept text toxicity propensity to characterize the extent to which a text tends to attract toxic comments. Beta regression is then introduced to do the probabilistic modeling, which is demonstrated to function well in comprehensive experiments. We also propose an explanation method to communicate the model decision clearly. Both propensity scoring and interpretation benefit text moderation in a novel manner. Finally, the proposed scaling mechanism for the linear model offers useful insights beyond this work. ...
Keyword: Computational Linguistics; Language Models; Machine Learning; Machine Learning and Data Mining; Natural Language Processing
URL: https://underline.io/lecture/37525-bert-beta-a-proactive-probabilistic-approach-to-text-moderation
https://dx.doi.org/10.48448/sagg-3962
BASE
Hide details
151
BERT Cannot Align Characters ...
BASE
Show details
152
ClauseRec: A Clause Recommendation Framework for AI-aided Contract Authoring ...
BASE
Show details
153
Improving Multimodal fusion via Mutual Dependency Maximisation ...
BASE
Show details
154
Jump-Starting Item Parameters for Adaptive Language Tests ...
BASE
Show details
155
Decoding Word Embeddings with Brain-Based Semantic Features ...
BASE
Show details
156
Skim-Attention: Learning to Focus via Document Layout ...
BASE
Show details
157
Automated Template Paraphrasing for Conversational Assistants ...
BASE
Show details
158
AUTOSUMM: Automatic Model Creation for Text Summarization ...
BASE
Show details
159
Understanding and Overcoming the Challenges of Efficient Transformer Quantization ...
BASE
Show details
160
Low-resource Taxonomy Enrichment with Pretrained Language Models ...
BASE
Show details

Page: 1...4 5 6 7 8 9 10 11 12...236

Catalogues
159
0
10
0
0
8
2
Bibliographies
929
0
0
0
0
0
0
19
95
Linked Open Data catalogues
0
Online resources
0
0
0
0
Open access documents
3.663
1
0
0
0
© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern