13197 research outputs found
Sort by
MAG-BERT-ARL for Fair Automated Video Interview Assessment
No full textPotential biases within automated video interview assessment algorithms may disadvantage specific demographics due to the collection of sensitive attributes, which are regulated by the General Data Protection Regulation (GDPR). To mitigate these fairness concerns, this research introduces MAG-BERT-ARL, an automated video interview assessment system that eliminates reliance on sensitive attributes. MAG-BERT-ARL integrates Multimodal Adaptation Gate and Bidirectional Encoder Representations from Transformers (MAG-BERT) model with the Adversarially Reweighted Learning (ARL). This integration aims to improve the performance of underrepresented groups by promoting Rawlsian Max-Min Fairness. Through experiments on the Educational Testing Service (ETS) and First Impressions (FI) datasets, the proposed method demonstrates its effectiveness in optimizing model performance (increasing Pearson correlation coefficient up to 0.17 in the FI dataset and precision up to 0.39 in the ETS dataset) and fairness (reducing equal accuracy up to 0.11 in the ETS dataset). The findings underscore the significance of integrating fairness-enhancing techniques like ARL and highlight the impact of incorporating nonverbal cues on hiring decisions.journal articl
Centroid-Based Efficient Minimum Bayes Risk Decoding
No full textMinimum Bayes risk (MBR) decoding achieved state-of-the-art translation performance by using COMET, a neural metric that has a high correlation with human evaluation.However, MBR decoding requires quadratic time since it computes the expected score between a translation hypothesis and all reference translations.We propose centroid-based MBR (CBMBR) decoding to improve the speed of MBR decoding.Our method clusters the reference translations in the feature space, and then calculates the score using the centroids of each cluster.The experimental results show that our CBMBR not only improved the decoding speed of the expected score calculation 5.7 times, but also outperformed vanilla MBR decoding in translation quality by up to 0.5 COMET in the WMT’22 En2194De, En2194Ja translation tasks.conference pape
Unified Interpretation of Smoothing Methods for Negative Sampling Loss Functions in Knowledge Graph Embedding
No full textKnowledge Graphs (KGs) are fundamental resources in knowledge-intensive tasks in NLP. Due to the limitation of manually creating KGs, KG Completion (KGC) has an important role in automatically completing KGs by scoring their links with KG Embedding (KGE). To handle many entities in training, KGE relies on Negative Sampling (NS) loss that can reduce the computational cost by sampling. Since the appearance frequencies for each link are at most one in KGs, sparsity is an essential and inevitable problem. The NS loss is no exception. As a solution, the NS loss in KGE relies on smoothing methods like Self-Adversarial Negative Sampling (SANS) and subsampling. However, it is uncertain what kind of smoothing method is suitable for this purpose due to the lack of theoretical understanding. This paper provides theoretical interpretations of the smoothing methods for the NS loss in KGE and induces a new NS loss, Triplet Adaptive Negative Sampling (TANS), that can cover the characteristics of the conventional smoothing methods. Experimental results of TransE, DistMult, ComplEx, RotatE, HAKE, and HousE on FB15k-237, WN18RR, and YAGO3-10 datasets and their sparser subsets show the soundness of our interpretation and performance improvement by our TANS.conference pape
Brassinosteroid signaling represses ZINC FINGER PROTEIN11 to regulate ovule development in Arabidopsis
Get PDFBrassinosteroid (BR) signaling and the C-class MADS-box gene AGAMOUS (AG) play important roles in ovule development in Arabidopsis (Arabidopsis thaliana). However, how BR signaling integrates with AG functions to control the female reproductive process remains elusive. Here, we showed that the regulatory role of BR signaling in proper ovule development is mediated by the transcriptional repressor gene ZINC FINGER PROTEIN 11 (ZFP11), which is a direct target of AG. ZFP11 expression initiates from the placenta upon AG induction and becomes prominent in the funiculus of ovule primordia. Plants harboring zfp11 mutations showed reduced placental length with decreased ovule numbers and some aborted ovules. During ovule development, the transcription factor BRASSINAZOLE-RESISTANT 1 (BZR1), which functions downstream of BR signaling, inhibits ZFP11 expression in the chalaza and nucellus. Weakened BR signaling leads to stunted integuments in ovules, resulting from the direct repression of INNER NO OUTER (INO) and WUSCHEL (WUS) by extended ZFP11 expression in the chalaza and nucellus, respectively. In addition, the zfp11 mutant shows reduced sensitivity to BR biosynthesis inhibitors and can rescue outer integument defects in brassinosteroid insensitive 1 (bri1) mutants. Thus, the precise spatial regulation of ZFP11, which is activated by AG in the placenta and suppressed by BR signaling in the central and distal regions of ovules, is essential for ensuring sufficient ovule numbers and proper ovule formation.journal articl
Improving the Image Discrimination Ability for CLIP-Model via Linguistic Structural Information
Get PDF奈良先端科学技術大学院大学修士(工学)master thesi
Sim-to-Real Reinforcement Learning with Low-fidelity Simulators and Extensive Domain Randomization for Complex Tasks
Get PDF奈良先端科学技術大学院大学博士(工学)doctoral thesi
Revolutionizing Robot Tactile Perception by Vibration Injection
Get PDF奈良先端科学技術大学院大学博士(工学)doctoral thesi
Improving Electricity Theft Detection for Smart Homes : Insights from Real and Synthetic Attack Scenarios
Get PDF奈良先端科学技術大学院大学博士(工学)doctoral thesi