Shortformer: Better Language Modeling using Shorter Inputs

ACL 2021  ·  Ofir Press, Noah A. Smith, Mike Lewis ·

Increasing the input length has been a driver of progress in language modeling with transformers. We identify conditions where shorter inputs are not harmful, and achieve perplexity and efficiency improvements through two new methods that decrease input length. First, we show that initially training a model on short subsequences before moving on to longer ones both reduces overall training time and, surprisingly, substantially improves perplexity. Second, we show how to improve the efficiency of recurrence methods in transformers, which let models condition on previously processed tokens when generating sequences that exceed the maximal length the transformer can handle at once. Existing methods require computationally expensive relative position embeddings; we introduce a simple alternative of adding absolute position embeddings to queries and keys instead of to word embeddings, which efficiently produces superior results. We show that these recurrent models also benefit from short input lengths. Combining these techniques speeds up training by a factor of 1.65, reduces memory usage, and substantially improves perplexity on WikiText-103, without adding any parameters.

PDF Abstract ACL 2021 PDF ACL 2021 Abstract

Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Language Modelling WikiText-103 Staged Training Validation perplexity 16.89 # 10
Test perplexity 17.56 # 26
Number of params 247M # 19
Language Modelling WikiText-103 Shortformer Validation perplexity 17.47 # 12
Test perplexity 18.15 # 31
Number of params 247M # 19