paper-with-me

Papers

Enhancing Length Extrapolation in Sequential Models with Pointer-Augmented Neural Memory

2024-04-18 · Hung Le, Dung Nguyen, Kien Do, Svetha Venkatesh, Truyen Tran

We propose Pointer-Augmented Neural Memory (PANM) to help neural networks understand and apply symbol processing to new, longer sequences of data. PANM integrates an external neural memory that uses novel physical addresses and pointer manipulation techniques to mimic human and computer symbol processing abilities. PANM facilitates pointer assignment, dereference, and arithmetic by explicitly using physical pointers to access memory content. Remarkably, it can learn to perform these operations through end-to-end training on sequence data, powering various sequential models. Our experiments demonstrate PANM's exceptional length extrapolating capabilities and improved performance in tasks that require symbol processing, such as algorithmic reasoning and Dyck language recognition. PANM helps Transformer achieve up to 100% generalization accuracy in compositional learning tasks and significantly better results in mathematical reasoning, question answering and machine translation tasks.

📄 PDF Abstract BibTeX arXiv:2404.11870

Code (0)

등록된 구현이 없습니다.

Tasks

Machine TranslationMathematical ReasoningQuestion Answering

Methods 이 논문이 사용한 방법론

Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Adam 설명 없음
Attention 설명 없음
Position-Wise Feed-Forward Layer 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Multi-Head Attention 설명 없음
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…

Similar Papers 제목 키워드 기반

Self Attended Stack-Pointer Networks for Learning Long Term Dependencies

2020-12-01 · ICON 2020 12 · Salih Tuc, Burcu Can

We propose a novel deep neural architecture for dependency parsing, which is built upon a Transformer Encoder (Vaswani et al. 2017) and a Stack Pointer Network (Ma et al. 2018). We first encode each sentence using a Tran…

Dependency ParsingSentence

SeqPE: Transformer with Sequential Position Encoding

2025-06-16 · Huayang Li, Yahui Liu, Hongyu Sun, Deng Cai 외

Since self-attention layers in Transformers are permutation invariant by design, positional encodings must be explicitly incorporated to enable spatial understanding. However, fixed-size lookup tables used in traditional…

image-classificationImage ClassificationKnowledge DistillationLanguage Modeling+3

Information Entropy Invariance: Enhancing Length Extrapolation in Attention Mechanisms

2025-01-15 · Kewei Li, Yanwen Kong, Yiping Xu, Jianlin Su 외

Since the emergence of research on improving the length extrapolation capabilities of large language models in 2021, some studies have made modifications to the scaling factor in the scaled dot-product attention mechanis…

LEDiT: Your Length-Extrapolatable Diffusion Transformer without Positional Encoding

2025-03-06 · Shen Zhang, Yaning Tan, Siyuan Liang, Linze Li 외

Diffusion transformers(DiTs) struggle to generate images at resolutions higher than their training resolutions. The primary obstacle is that the explicit positional encodings(PE), such as RoPE, need extrapolation which d…

Pointer-Guided Pre-Training: Infusing Large Language Models with Paragraph-Level Contextual Awareness

2024-06-06 · Lars Hillebrand, Prabhupad Pradhan, Christian Bauckhage, Rafet Sifa

We introduce "pointer-guided segment ordering" (SO), a novel pre-training technique aimed at enhancing the contextual understanding of paragraph-level text representations in large language models. Our methodology levera…

Diversitytext-classificationText Classification