Papers › Adaptive Input Representations for Neural Language Modeling
Adaptive Input Representations for Neural Language Modeling
Alexei Baevski, Michael Auli
We introduce adaptive input representations for neural language modeling which extend the adaptive softmax of Grave et al. (2017) to input representations of variable capacity. There are several choices on how to factorize the input and output layers, and whether to model words, characters or sub-word units. We perform a systematic comparison of popular choices for a self-attentional architecture. Our experiments show that models equipped with adaptive embeddings are more than twice as fast to train than the popular character input CNN while having a lower number of parameters. On the WikiText-103 benchmark we achieve 18.7 perplexity, an improvement of 10.5 perplexity compared to the previously best published result and on the Billion Word benchmark, we achieve 23.02 perplexity.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Language Modelling | One Billion Word | Adaptive Input Very Large | Number of params | 1.0B | #7 of 27 | Archive leaderboard | report |
| Language Modelling | One Billion Word | Adaptive Input Very Large | PPL | 23.02 | #7 of 27 | Archive leaderboard | report |
| Language Modelling | One Billion Word | Adaptive Input Very Large | Validation perplexity | 22.92 | #7 of 27 | Archive leaderboard | report |
| Language Modelling | One Billion Word | Adaptive Input Large | Number of params | 0.46B | #11 of 27 | Archive leaderboard | report |
| Language Modelling | One Billion Word | Adaptive Input Large | PPL | 23.91 | #11 of 27 | Archive leaderboard | report |
| Language Modelling | One Billion Word | Adaptive Input Large | Validation perplexity | 23.83 | #11 of 27 | Archive leaderboard | report |
| Language Modelling | WikiText-103 | Transformer (Adaptive inputs) | Number of params | 247M | #40 of 89 | Archive leaderboard | report |
| Language Modelling | WikiText-103 | Transformer (Adaptive inputs) | Test perplexity | 18.70 | #40 of 89 | Archive leaderboard | report |
| Language Modelling | WikiText-103 | Transformer (Adaptive inputs) | Validation perplexity | 17.97 | #40 of 89 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Methods
Introduced by this paper: Adaptive Input Representations
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections