1 |
On Classifying whether Two Texts are on the Same Side of an Argument ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
Transfer Learning from LDA to BiLSTM-CNN for Offensive Language Detection in Twitter
|
|
|
|
In: http://hw.oeaw.ac.at/8435-5 (2018)
|
|
Abstract:
We investigate different strategies for automatic offensive language classification on German Twitter data. For this, we employ a sequentially combined BiLSTMCNN neural network. Based on this model, three transfer learning tasks to improve the classification performance with background knowledge are tested. We compare 1. Supervised category transfer: social media data annotated with near-offensive language categories, 2. Weakly-supervised category transfer: tweets annotated with emojis they contain, 3. Unsupervised category transfer: tweets annotated with topic clusters obtained by Latent Dirichlet Allocation (LDA). Further, we investigate the effect of three different strategies to mitigate negative effects of ‘catastrophic forgetting’ during transfer learning. Our results indicate that transfer learning in general improves offensive language detection. Best results are achieved from pre-training our model on the unsupervised topic clustering of tweets in combination with thematic user cluster information.
|
|
Keyword:
Linguistics and Literature
|
|
URL: http://epub.oeaw.ac.at/?arp=buecher/Organisationseinheiten/academiae-corpora/Proceedings%20of%20the%20GermEval%202018Workshop/015_GermEval2018_Proceedings.pdf
|
|
BASE
|
|
Hide details
|
|
4 |
A Multilingual Information Extraction Pipeline for Investigative Journalism ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
New/s/leak 2.0 - Multilingual Information Extraction and Visualization for Investigative Journalism ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
Quantifying insightful problem solving: A modified compound remote associates paradigm using lexical priming to parametrically modulate different sources of task difficulty ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
Modeling the dynamics of domain specific terminology in diachronic corpora ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
Leipzig Corpus Miner - A Text Mining Infrastructure for Qualitative Data Analysis ...
|
|
|
|
BASE
|
|
Show details
|
|
9 |
Opening up to big data: computer-assisted analysis of textual data in social sciences
|
|
|
|
In: Historical Social Research ; 38 ; 4 ; 332-358 (2015)
|
|
BASE
|
|
Show details
|
|
10 |
Leipzig Corpus Miner - A Text Mining Infrastructure for Qualitative Data Analysis
|
|
|
|
In: Terminology and Knowledge Engineering, TKE 2014 ; Terminology and Knowledge Engineering 2014 ; https://hal.archives-ouvertes.fr/hal-01005878 ; Terminology and Knowledge Engineering 2014, Jun 2014, Berlin, Germany. 10 p (2014)
|
|
BASE
|
|
Show details
|
|
11 |
Opening up to big data: computer-assisted analysis of textual data in social sciences
|
|
|
|
In: Forum Qualitative Sozialforschung / Forum: Qualitative Social Research ; 14 ; 2 ; 24 (2013)
|
|
BASE
|
|
Show details
|
|
|
|