paper-with-me

홈 › Papers

A Tensorized Transformer for Language Modeling

2019-06-24 · NeurIPS 2019 12 · Xindian Ma, Peng Zhang, Shuai Zhang, Nan Duan, Yuexian Hou, Dawei Song, Ming Zhou

Latest development of neural models has connected the encoder and decoder through a self-attention mechanism. In particular, Transformer, which is solely based on self-attention, has led to breakthroughs in Natural Language Processing (NLP) tasks. However, the multi-head attention mechanism, as a key component of Transformer, limits the effective deployment of the model to a resource-limited setting. In this paper, based on the ideas of tensor decomposition and parameters sharing, we propose a novel self-attention model (namely Multi-linear attention) with Block-Term Tensor Decomposition (BTD). We test and verify the proposed attention method on three language modeling tasks (i.e., PTB, WikiText-103 and One-billion) and a neural machine translation task (i.e., WMT-2016 English-German). Multi-linear attention can not only largely compress the model parameters but also obtain performance improvements, compared with a number of language modeling approaches, such as Transformer, Transformer-XL, and Transformer with tensor train decomposition.

📄 PDF Abstract BibTeX arXiv:1906.09777

Code (1)

szhangtju/The-compression-of-Transformer 공식 구현 pytorch

Tasks

DecoderLanguage ModelingLanguage ModellingMachine TranslationTensor DecompositionTranslation

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Position-Wise Feed-Forward Layer 설명 없음
Cosine Annealing Cosine Annealing is a type of learning rate schedule that has the effect of starting with a large learning rate that is relatively rapidly decreased to a minimum value before…
Variational Dropout Variational Dropout is a regularization technique based on dropout, but uses a variational inference grounded approach. In…
Adaptive Input Representations Adaptive Input Embeddings extend the adaptive softmax to input word representations. The factorization assigns more…
Adaptive Softmax Adaptive Softmax is a speedup technique for the computation of probability distributions over words. The adaptive softmax is…
Linear Warmup With Cosine Annealing Linear Warmup With Cosine Annealing is a learning rate schedule where we increase the learning rate linearly for $n$ updates and then anneal according to a cosine schedule…

Similar Papers 제목 키워드 기반

Tensorized Transformer for Dynamical Systems Modeling

2020-06-05 · Anna Shalova, Ivan Oseledets

The identification of nonlinear dynamics from observations is essential for the alignment of the theoretical ideas and experimental data. The last, in turn, is often corrupted by the side effects and noise of different n…

Language ModelingLanguage Modelling

Long Sequence Modeling with Attention Tensorization: From Sequence to Tensor Learning

2024-10-28 · Aosong Feng, Rex Ying, Leandros Tassiulas

As the demand for processing extended textual data grows, the ability to handle long-range dependencies and maintain computational efficiency is more critical than ever. One of the key issues for long-sequence modeling u…

Computational Efficiency

Tensorizing Engram: Sharing Latents Across N-Gram Embeddings is Beneficial in LLMs

2026-06-06 · Wuyang Zhou, Yuxuan Gu, Giorgos Iacovides, Yuning Qiu 외 arxiv

Modern language models represent text using discrete token-level embeddings, which forces recurring multi-token patterns to be learned implicitly across Transformer layers. Both Over-tokenized Transformers and Engram att…

A tensorized logic programming language for large-scale data

2019-01-20 · Ryosuke Kojima, Taisuke Sato

We introduce a new logic programming language T-PRISM based on tensor embeddings. Our embedding scheme is a modification of the distribution semantics in PRISM, one of the state-of-the-art probabilistic logic programming…

Knowledge Graphs

Partial Tensorized Transformers for Natural Language Processing

2023-10-30 · Subhadra Vadlamannati, Ryan Solgi

The transformer architecture has revolutionized Natural Language Processing (NLP) and other machine-learning tasks, due to its unprecedented accuracy. However, their extensive memory and parameter requirements often hind…

Tensor Decomposition