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

4 Nov 2016arXiv:1611.01462archive 2025-07-28

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.

PaperPDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

InnerPeace-Wu/im2p-tensorflow mentioned on GitHubtfMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to A Hierarchical Approach for Generating Descriptive Image Paragraphs (arXiv:1611.06607; that paper's own run record: 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. report
JianGoForIt/YellowFin_Pytorch mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Aggregated Residual Transformations for Deep Neural Networks (arXiv:1611.05431; that paper's own run record: 51 ran (of which 7 constructed an object rather than computing a result; 31 with no instrument failure: 0 honoured, 0 violated, 31 with no contract checked; 20 where Syntology's instrument failed) · 29 unverified); nothing checks that they implement this paper's method. report
Ravoxsg/Word-level-language-modeling mentioned on GitHubpytorchSyntology: not harvested report
floydhub/word-language-model mentioned on GitHubpytorchSyntology: not harvested report
rdspring1/PyTorch_GBW_LM mentioned on GitHubpytorchSyntology: not harvested report

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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

General ClassificationLanguage ModelingLanguage Modelling

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
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

Weight Tying

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