Search Results for author:
Found 4 papers, 3 papers with code
Searching for Optimal Subword Tokenization in Cross-domain NER
Input distribution shift is one of the vital problems in unsupervised domain adaptation (UDA).
Plug-Tagger: A Pluggable Sequence Labeling Framework Using Language Models
Specifically, for each task, a label word set is first constructed by selecting a high-frequency word for each class respectively, and then, task-specific vectors are inserted into the inputs and optimized to manipulate the model predictions towards the corresponding label words.
Template-free Prompt Tuning for Few-shot NER
Prompt-based methods have been successfully applied in sentence-level few-shot learning tasks, mostly owing to the sophisticated design of templates and label words.
TextFlint: Unified Multilingual Robustness Evaluation Toolkit for Natural Language Processing
To guarantee user acceptability, all the text transformations are linguistically based, and we provide a human evaluation for each one.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
