Search Results for author:
Found 8 papers, 4 papers with code
Listener’s Social Identity Matters in Personalised Response Generation
Personalised response generation enables generating human-like responses by means of assigning the generator a social identity.
Understanding Gender Bias in Knowledge Base Embeddings
To exemplify the potential applications of our study, we also present two strategies (by adding and removing KB triples) to mitigate gender biases in KB embeddings.
FTFT: Efficient and Robust Fine-Tuning by Transferring Training Dynamics
Dataset cartography is a simple yet effective dual-model approach that improves the robustness of fine-tuned PLMs.
CREATED: Generating Viable Counterfactual Sequences for Predictive Process Analytics
Current methods to generate counterfactual sequences either do not take the process behavior into account, leading to generating invalid or infeasible counterfactual process instances, or heavily rely on domain knowledge.
Measuring the Instability of Fine-Tuning
Fine-tuning pre-trained language models on downstream tasks with varying random seeds has been shown to be unstable, especially on small datasets.
Assessing the Reliability of Word Embedding Gender Bias Measures
In this paper, we assess three types of reliability of word embedding gender bias measures, namely test-retest reliability, inter-rater consistency and internal consistency.
Listener's Social Identity Matters in Personalised Response Generation
Personalised response generation enables generating human-like responses by means of assigning the generator a social identity.
Exploring Human Gender Stereotypes with Word Association Test
Specifically, we use random walk on word association graph to derive bias scores for a large amount of words.
