Search Results for author: Lucas Liu

Found 2 papers, 1 papers with code

Multi-Head Adapter Routing for Data-Efficient Fine-Tuning

no code implementations7 Nov 2022 Lucas Caccia, Edoardo Ponti, Lucas Liu, Matheus Pereira, Nicolas Le Roux, Alessandro Sordoni

In particular, we find that instruction tuning, where models are fully fine-tuned on natural language instructions for each task, is inferior to modular methods such as Polytropon and our proposed variants.

Multi-Task Learning

BERTifying the Hidden Markov Model for Multi-Source Weakly Supervised Named Entity Recognition

2 code implementations ACL 2021 Yinghao Li, Pranav Shetty, Lucas Liu, Chao Zhang, Le Song

To address this challenge, we propose a conditional hidden Markov model (CHMM), which can effectively infer true labels from multi-source noisy labels in an unsupervised way.

named-entity-recognition NER +1

Cannot find the paper you are looking for? You can Submit a new open access paper.