mlsanityData to 14 Oct 2026

Tying Word Vectors and Word Classifiers: A Loss Framework for Language Modeling

arXiv 1611.01462 ↗First posted 4 Nov 2016cs.LG cs.CL stat.MLcited by 92

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 92 papers in the map (data through 14 Oct 2026). First posted on arXiv 4 Nov 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 25; 2022: 15; 2023: 15; 2024: 10; 2025: 8; 2026: 19.

92 papers.

Sort:

By area:

  1. 2021Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolationcited by 1,103
  2. 2023The Falcon Series of Open Language Modelscited by 535
  3. 2021Training Graph Neural Networks with 1000 Layerscited by 169
  4. 2023The mechanistic basis of data dependence and abrupt learning in an in-context classification taskcited by 118
  5. 2024Language models scale reliably with over-training and on downstream taskscited by 113
  6. 2021Finetuning Pretrained Transformers into RNNscited by 96
  7. 2021Adaptive Semiparametric Language Modelscited by 83
  8. 2023Tied-Lora: Enhancing parameter efficiency of LoRA with weight tyingcited by 65
  9. 2023Spike No More: Stabilizing the Pre-training of Large Language Modelscited by 52
  10. 2024Fishing for Magikarp: Automatically Detecting Under-trained Tokens in Large Language Modelscited by 46
  11. 2021Tied & Reduced RNN-T Decodercited by 36
  12. 2022FLCert: Provably Secure Federated Learning against Poisoning Attackscited by 30
38 more
  1. 2021Selfish Sparse RNN Trainingcited by 26
  2. 2022Wav2Seq: Pre-training Speech-to-Text Encoder-Decoder Models Using Pseudo Languagescited by 26
  3. 2022Efficient recurrent architectures through activity sparsity and sparse back-propagation through timecited by 26
  4. 2021Hybrid Random Featurescited by 25
  5. 2022Relational Memory Augmented Language Modelscited by 24
  6. 2021How Does Fine-tuning Affect the Geometry of Embedding Space: A Case Study on Isotropycited by 23
  7. 2021Convex Aggregation for Opinion Summarizationcited by 21
  8. 2022Multilingual Machine Translation with Hyper-Adapterscited by 15
  9. 2023Tensor Decomposition for Model Reduction in Neural Networks: A Reviewcited by 14
  10. 2026Solve the Loop: Attractor Models for Language and Reasoningcited by 13
  11. 2021InvBERT: Reconstructing Text from Contextualized Word Embeddings by inverting the BERT pipelinecited by 11
  12. 2021Frequency-Aware Contrastive Learning for Neural Machine Translationcited by 11
  13. 2022Generalization in Neural Networks: A Broad Surveycited by 11
  14. 2024What makes math problems hard for reinforcement learning: a case studycited by 9
  15. 2021The Rediscovery Hypothesis: Language Models Need to Meet Linguisticscited by 7
  16. 2021Transformers with multi-modal features and post-fusion context for e-commerce session-based recommendationcited by 7
  17. 2023Coordinating Distributed Example Orders for Provably Accelerated Trainingcited by 7
  18. 2024Masked Generative Priors Improve World Models Sequence Modelling Capabilitiescited by 7
  19. 2025Exploiting Vocabulary Frequency Imbalance in Language Model Pre-trainingcited by 7
  20. 2024Stable Language Model Pre-training by Reducing Embedding Variabilitycited by 6
  21. 2024From Word Vectors to Multimodal Embeddings: Techniques, Applications, and Future Directions For Large Language Modelscited by 6
  22. 2025PiCa: Parameter-Efficient Fine-Tuning with Column Space Projectioncited by 6
  23. 2021Doping: A technique for efficient compression of LSTM models using sparse structured additive matricescited by 5
  24. 2022Joint Generation of Captions and Subtitles with Dual Decodingcited by 5
  25. 2024Disentangling and Integrating Relational and Sensory Information in Transformer Architecturescited by 5
  26. 2024DEPT: Decoupled Embeddings for Pre-training Language Modelscited by 5
  27. 2021Neural Architecture Search for Image Super-Resolution Using Densely Constructed Search Space: DeCoNAScited by 4
  28. 2022Automatic Sparse Connectivity Learning for Neural Networkscited by 4
  29. 2022Linearizing Transformer with Key-Value Memorycited by 4
  30. 2022Twist Decoding: Diverse Generators Guide Each Othercited by 4
  31. 2022ViGAT: Bottom-up event recognition and explanation in video using factorized graph attention networkcited by 4
  32. 2022ConsistTL: Modeling Consistency in Transfer Learning for Low-Resource Neural Machine Translationcited by 4
  33. 2024Kraken: Inherently Parallel Transformers For Efficient Multi-Device Inferencecited by 4
  34. 2021Attention vs non-attention for a Shapley-based explanation methodcited by 3
  35. 2021Spectral Pruning for Recurrent Neural Networkscited by 3
  36. 2021Exploring Unsupervised Pretraining Objectives for Machine Translationcited by 3
  37. 2023Longer Fixations, More Computation: Gaze-Guided Recurrent Neural Networkscited by 3
  38. 2025SURFing to the Fundamental Limit of Jet Taggingcited by 3

50 most cited of 92 All 92 (JSON)