LAMOL: LAnguage MOdeling for Lifelong Language Learning

ICLR 2020  ·  Fan-Keng Sun, Cheng-Hao Ho, Hung-Yi Lee ·

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.

PDF Abstract ICLR 2020 PDF ICLR 2020 Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Continual Learning 20Newsgroup (10 tasks) LAMOL F1 - macro 0.4572 # 6
Continual Learning ASC (19 tasks) LAMOL F1 - macro 0.8059 # 4

Methods


No methods listed for this paper. Add relevant methods here