LAMOL: LAnguage MOdeling for Lifelong Language Learning

September 07, 2019 · Entered Twilight · 🏛 International Conference on Learning Representations

"Last commit was 5.0 years ago (≥5 year threshold)"

Evidence collected by the PWNC Scanner

Repo contents: LICENSE, README.md, data_attrs.json, env.example, fp16.py, fp16util.py, loss_scaler.py, metrics.py, parallel.py, preprocess.py, regularizers.py, requirements.txt, scheduler.py, settings.py, test.py, test.sh, train.py, train.sh, utils.py

Authors Fan-Keng Sun, Cheng-Hao Ho, Hung-Yi Lee arXiv ID 1909.03329 Category cs.CL: Computation & Language Cross-listed cs.AI Citations 243 Venue International Conference on Learning Representations Repository https://github.com/jojotenya/LAMOL ⭐ 95 Last Checked 1 month ago

Abstract

Most research on lifelong learning applies to images or games, but not language. We present LAMOL, a simple yet effective method for lifelong language learning (LLL) based on language modeling. LAMOL replays pseudo-samples of previous tasks while requiring no extra memory or model capacity. Specifically, LAMOL is a language model that simultaneously learns to solve the tasks and generate training samples. When the model is trained for a new task, it generates pseudo-samples of previous tasks for training alongside data for the new task. The results show that LAMOL prevents catastrophic forgetting without any sign of intransigence and can perform five very different language tasks sequentially with only one model. Overall, LAMOL outperforms previous methods by a considerable margin and is only 2-3% worse than multitasking, which is usually considered the LLL upper bound. The source code is available at https://github.com/jojotenya/LAMOL.