Page: 1... 3 4 5 6 7 8 9 10 11... 150
121 |
PALI-NLP at SemEval-2022 Task 4: Discriminative Fine-tuning of Deep Transformers for Patronizing and Condescending Language Detection ...
|
|
|
|
BASE
|
|
Show details
|
|
122 |
Compilable Neural Code Generation with Compiler Feedback ...
|
|
|
|
BASE
|
|
Show details
|
|
123 |
GatorTron: A Large Clinical Language Model to Unlock Patient Information from Unstructured Electronic Health Records ...
|
|
|
|
BASE
|
|
Show details
|
|
124 |
Mental Disorders on Online Social Media Through the Lens of Language and Behaviour: Analysis and Visualisation ...
|
|
|
|
BASE
|
|
Show details
|
|
126 |
FALCON: Fast Visual Concept Learning by Integrating Images, Linguistic descriptions, and Conceptual Relations ...
|
|
|
|
BASE
|
|
Show details
|
|
128 |
Rethinking Offensive Text Detection as a Multi-Hop Reasoning Problem ...
|
|
|
|
BASE
|
|
Show details
|
|
129 |
Chain-based Discriminative Autoencoders for Speech Recognition ...
|
|
|
|
BASE
|
|
Show details
|
|
130 |
Unsupervised word-level prosody tagging for controllable speech synthesis ...
|
|
|
|
BASE
|
|
Show details
|
|
131 |
AI-Based Automated Speech Therapy Tools for persons with Speech Sound Disorders: A Systematic Literature Review ...
|
|
|
|
BASE
|
|
Show details
|
|
132 |
UBERT: A Novel Language Model for Synonymy Prediction at Scale in the UMLS Metathesaurus ...
|
|
|
|
BASE
|
|
Show details
|
|
133 |
gTLO: A Generalized and Non-linear Multi-Objective Deep Reinforcement Learning Approach ...
|
|
|
|
BASE
|
|
Show details
|
|
134 |
Inferring Lexicographically-Ordered Rewards from Preferences ...
|
|
|
|
Abstract:
Modeling the preferences of agents over a set of alternatives is a principal concern in many areas. The dominant approach has been to find a single reward/utility function with the property that alternatives yielding higher rewards are preferred over alternatives yielding lower rewards. However, in many settings, preferences are based on multiple, often competing, objectives; a single reward function is not adequate to represent such preferences. This paper proposes a method for inferring multi-objective reward-based representations of an agent's observed preferences. We model the agent's priorities over different objectives as entering lexicographically, so that objectives with lower priorities matter only when the agent is indifferent with respect to objectives with higher priorities. We offer two example applications in healthcare, one inspired by cancer treatment, the other inspired by organ transplantation, to illustrate how the lexicographically-ordered rewards we learn can provide a better ... : In Proceedings of the 36th AAAI Conference on Artificial Intelligence ...
|
|
Keyword:
Artificial Intelligence cs.AI; FOS Computer and information sciences; Machine Learning cs.LG; Machine Learning stat.ML
|
|
URL: https://dx.doi.org/10.48550/arxiv.2202.10153 https://arxiv.org/abs/2202.10153
|
|
BASE
|
|
Hide details
|
|
135 |
Cross-Platform Difference in Facebook and Text Messages Language Use: Illustrated by Depression Diagnosis ...
|
|
|
|
BASE
|
|
Show details
|
|
136 |
Improving Word Translation via Two-Stage Contrastive Learning ...
|
|
|
|
BASE
|
|
Show details
|
|
137 |
New Core-Guided and Hitting Set Algorithms for Multi-Objective Combinatorial Optimization ...
|
|
|
|
BASE
|
|
Show details
|
|
138 |
Research on Dual Channel News Headline Classification Based on ERNIE Pre-training Model ...
|
|
|
|
BASE
|
|
Show details
|
|
139 |
Improving Zero-Shot Event Extraction via Sentence Simplification ...
|
|
|
|
BASE
|
|
Show details
|
|
140 |
Language Models Explain Word Reading Times Better Than Empirical Predictability ...
|
|
|
|
BASE
|
|
Show details
|
|
Page: 1... 3 4 5 6 7 8 9 10 11... 150
|
|