Search Results for author:
Found 4 papers, 1 papers with code
Asynchronous Convergence in Multi-Task Learning via Knowledge Distillation from Converged Tasks
However, one issue that often arises in MTL is the convergence speed between tasks varies due to differences in task difficulty, so it can be a challenge to simultaneously achieve the best performance on all tasks with a single model checkpoint.
DynaMaR: Dynamic Prompt with Mask Token Representation
In this paper, we propose an improvement to prompt-based fine-tuning that addresses these two issues.
Embracing Structure in Data for Billion-Scale Semantic Product Search
When training a dyadic model, one seeks to embed two different types of entities (e. g., queries and documents or users and movies) in a common vector space such that pairs with high relevance are positioned nearby.
Semantic Product Search
To address these issues, we train a deep learning model for semantic matching using customer behavior data.
