Papers › Alleviating Sequence Information Loss with Data Overlapping and Prime Batch Sizes
Alleviating Sequence Information Loss with Data Overlapping and Prime Batch Sizes
Noémien Kocher, Christian Scuito, Lorenzo Tarantino, Alexandros Lazaridis, Andreas Fischer, Claudiu Musat
In sequence modeling tasks the token order matters, but this information can be partially lost due to the discretization of the sequence into data points. In this paper, we study the imbalance between the way certain token pairs are included in data points and others are not. We denote this a token order imbalance (TOI) and we link the partial sequence information loss to a diminished performance of the system as a whole, both in text and speech processing tasks. We then provide a mechanism to leverage the full token order information -Alleviated TOI- by iteratively overlapping the token composition of data points. For recurrent networks, we use prime numbers for the batch size to avoid redundancies when building batches from overlapped data points. The proposed method achieved state of the art performance in both text and speech related tasks.
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 | WikiText-103 | AWD-LSTM-MoS + ATOI | Test perplexity | 32.85 | #74 of 89 | Archive leaderboard | report |
| Language Modelling | WikiText-103 | AWD-LSTM-MoS + ATOI | Validation perplexity | 31.92 | #74 of 89 | Archive leaderboard | report |
| Language Modelling | WikiText-2 | AWD-LSTM + ATOI | Number of params | 33M | #30 of 38 | Archive leaderboard | report |
| Language Modelling | WikiText-2 | AWD-LSTM + ATOI | Test perplexity | 64.73 | #30 of 38 | Archive leaderboard | report |
| Language Modelling | WikiText-2 | AWD-LSTM + ATOI | Validation perplexity | 67.47 | #30 of 38 | 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.
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