paper-with-me

Papers

LoPE: Learnable Sinusoidal Positional Encoding for Improving Document Transformer Model

2022-01-16 · ACL ARR January 2022 1 · Anonymous

Positional encoding plays a key role in Transformer-based architecture, which is to indicate and embed token sequential order information. Understanding documents with unreliable reading order information is a real challenge for document Transformer model. This paper proposes a new and generic positional encoding method, learnable sinusoidal positional encoding (LoPE), by combining sinusoidal positional encoding function and a learnable feed-forward network. We apply LoPE to document Transformer model and pretrain the model on document datasets. Then we finetune and evaluate the model performance on document understanding tasks in form and receipt domains. Experimental results not only show our proposed method outperforms other baselines and state-of-the-arts, but also demonstrate its robustness and stability on handling noisy data with incorrect order information.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

document understanding

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Residual Connection 설명 없음
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
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…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…

Similar Papers 제목 키워드 기반

The Impact of Positional Encodings on Multilingual Compression

2021-09-11 · EMNLP 2021 11 · Vinit Ravishankar, Anders Søgaard

In order to preserve word-order information in a non-autoregressive setting, transformer architectures tend to include positional knowledge, by (for instance) adding positional encodings to token embeddings. Several modi…

Inductive Bias

Lightweight Text Classifier using Sinusoidal Positional Encoding

2020-12-01 · Asian Chapter of the Association for Computational Linguistics 2020 · Byoung-Doo Oh, Yu-Seop Kim

Large and complex models have recently been developed that require many parameters and much time to solve various problems in natural language processing. This paper explores an efficient way to avoid models being too co…

Positiontext-classificationText Classification

Alternative positional encoding functions for neural transformers

2025-12-22 · Ezequiel Lopez-Rubio, Macoris Decena-Gimenez, Rafael Marcos Luque-Baena arxiv

A key module in neural transformer-based deep architectures is positional encoding. This module enables a suitable way to encode positional information as input for transformer neural layers. This success has been rooted…

Improving Transformers using Faithful Positional Encoding

2024-05-15 · Tsuyoshi Idé, Jokin Labaien, Pin-Yu Chen

We propose a new positional encoding method for a neural network architecture called the Transformer. Unlike the standard sinusoidal positional encoding, our approach is based on solid mathematical grounds and has a guar…

Time SeriesTime Series Classification

Spiking Sequence Machines and Transformers

2026-05-01 · Joy Bose arxiv

Sequence learning reduces to similarity-based retrieval over a temporally indexed representation space, a constraint on any sequence model, not a property of a specific architecture. We show that a spiking Sparse Distrib…