Labeled Examples
Related Papers
An Empirical Study of Active Learning with Support Vector Machines forJapanese Word Segmentation
We explore how active learning with Sup- port Vector Machines works well for a non-trivial task in natural language pro- cessing. We use Japanese word segmenta- tion as a test …...
Using Smaller Constituents Rather Than Sentences in Active Learning for Japanese Dependency Parsing
We investigate active learning methods for Japanese dependency parsing. We propose active learning methods of using partial dependency relations in a given sentence for parsing and evaluate their effective- ness …...
Muppet: Massive Multi-task Representations with Pre-Finetuning
AbstractWe propose pre-finetuning, an additional large-scale learning stage between language model pre-training and fine-tuning. Pre-finetuning is massively multi-task learning (around 50 datasets, over 4.8 million total labeled examples), and is …...
Fixing Model Bugs with Natural Language Patches
AbstractCurrent approaches for fixing systematic problems in NLP models (e.g., regex patches, finetuning on more data) are either brittle, or labor-intensive and liable to shortcuts. In contrast, humans often provide …...