Papers › Tying Word Vectors and Word Classifiers: A Loss Framework for Language Modeling
Tying Word Vectors and Word Classifiers: A Loss Framework for Language Modeling
Hakan Inan, Khashayar Khosravi, Richard Socher
Recurrent neural networks have been very successful at predicting sequences of words in tasks such as language modeling. However, all such models are based on the conventional classification framework, where the model is trained against one-hot targets, and each word is represented both as an input and as an output in isolation. This causes inefficiencies in learning both in terms of utilizing all of the information and in terms of the number of parameters needed to train. We introduce a novel theoretical framework that facilitates better learning in language modeling, and show that our framework leads to tying together the input embedding and the output projection matrices, greatly reducing the number of trainable variables. Our framework leads to state of the art performance on the Penn Treebank with a variety of network models.
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 | Penn Treebank (Word Level) | Inan et al. (2016) - Variational RHN | Test perplexity | 66.0 | #34 of 43 | Archive leaderboard | report |
| Language Modelling | Penn Treebank (Word Level) | Inan et al. (2016) - Variational RHN | Validation perplexity | 68.1 | #34 of 43 | Archive leaderboard | report |
| Language Modelling | WikiText-2 | Inan et al. (2016) - Variational LSTM (tied) (h=650) + augmented loss | Test perplexity | 87.0 | #35 of 38 | Archive leaderboard | report |
| Language Modelling | WikiText-2 | Inan et al. (2016) - Variational LSTM (tied) (h=650) + augmented loss | Validation perplexity | 91.5 | #35 of 38 | Archive leaderboard | report |
| Language Modelling | WikiText-2 | Inan et al. (2016) - Variational LSTM (tied) (h=650) | Test perplexity | 87.7 | #36 of 38 | Archive leaderboard | report |
| Language Modelling | WikiText-2 | Inan et al. (2016) - Variational LSTM (tied) (h=650) | Validation perplexity | 92.3 | #36 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.
Methods
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