AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

A Generalized Language Model in Tensor Space

Lipeng Zhang, Peng Zhang, Xindian Ma, Shuqin Gu, Zhan Su, Dawei Song

AAAI 2019 · Architectures and efficiency › RNNs and normalization · approach: Non-autoregressive translation

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use TSLM instead of reimplemented RNNLanguage modeling · PTB testperplexity: 124.1 -> 108.1Improved
Use TSLM instead of reimplemented LSTMLanguage modeling · PTB testperplexity: 110.3 -> 108.1Improved
Use TSLM instead of reimplemented RNNLanguage modeling · WikiText-2 testperplexity: 120.4 -> 100.4Improved
Use TSLM instead of reimplemented LSTMLanguage modeling · WikiText-2 testperplexity: 101.4 -> 100.4Improved
Use TSLM+MoS instead of RNN+MoSMoS language modeling · PTB testperplexity: 84.3 -> 83.6Improved
Use TSLM+MoS instead of RNN+MoSMoS language modeling · WikiText-2 testperplexity: 81.8 -> 81.0Improved
Increase tensor order / maximum sequence length up to the dataset-specific optimum (ablation)TSLM · PTB and WikiText-2perplexityMixed
Increase decomposition rank up to the dataset-specific optimum (ablation)TSLM · PTB and WikiText-2perplexityMixed

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy