English
Related papers

Related papers: The Curious Case of Absolute Position Embeddings

200 papers

While word embeddings are currently predominant for natural language processing, most of existing models learn them solely from their contexts. However, these context-based word embeddings are limited since not all words' meaning can be…

Computation and Language · Computer Science 2016-08-23 Jifan Chen , Kan Chen , Xipeng Qiu , Qi Zhang , Xuanjing Huang , Zheng Zhang

In contrast to fully connected networks, Convolutional Neural Networks (CNNs) achieve efficiency by learning weights associated with local filters with a finite spatial extent. An implication of this is that a filter may know what it is…

Computer Vision and Pattern Recognition · Computer Science 2020-01-24 Md Amirul Islam , Sen Jia , Neil D. B. Bruce

Positional encoding plays a crucial role in transformers, significantly impacting model performance and length generalization. Prior research has introduced absolute positional encoding (APE) and relative positional encoding (RPE) to…

Computation and Language · Computer Science 2024-11-06 Chuanyang Zheng , Yihang Gao , Han Shi , Minbin Huang , Jingyao Li , Jing Xiong , Xiaozhe Ren , Michael Ng , Xin Jiang , Zhenguo Li , Yu Li

Neural language models process sequences of words, but the mathematical operations inside them are insensitive to the order in which words appear. Positional encodings are the component added to remedy this. Despite their importance,…

Machine Learning · Computer Science 2026-04-08 Giansalvo Cirrincione

Recent advances in learning aligned multimodal representations have been primarily driven by training large neural networks on massive, noisy paired-modality datasets. In this work, we ask whether it is possible to achieve similar results…

Machine Learning · Computer Science 2022-10-11 Elan Rosenfeld , Preetum Nakkiran , Hadi Pouransari , Oncel Tuzel , Fartash Faghri

Transformers rely on positional encoding to compensate for the inherent permutation invariance of self-attention. Traditional approaches use absolute sinusoidal embeddings or learned positional vectors, while more recent methods emphasize…

Machine Learning · Computer Science 2025-11-18 Chase van de Geijn , Ayush Paliwal , Timo Lüddecke , Alexander S. Ecker

This paper proposes a model to learn word embeddings with weighted contexts based on part-of-speech (POS) relevance weights. POS is a fundamental element in natural language. However, state-of-the-art word embedding models fail to consider…

Computation and Language · Computer Science 2016-03-25 Quan Liu , Zhen-Hua Ling , Hui Jiang , Yu Hu

Word embeddings are one of the most useful tools in any modern natural language processing expert's toolkit. They contain various types of information about each word which makes them the best way to represent the terms in any NLP task. But…

Computation and Language · Computer Science 2019-06-20 Armin Seyeditabari , Narges Tabari , Shafie Gholizade , Wlodek Zadrozny

Language Models (LMs) have shown state-of-the-art performance in Natural Language Processing (NLP) tasks. Downstream tasks such as Named Entity Recognition (NER) or Part-of-Speech (POS) tagging are known to suffer from data imbalance…

Computation and Language · Computer Science 2024-04-12 Mehdi Ben Amor , Michael Granitzer , Jelena Mitrović

The Rotary Position Embedding (RoPE) mechanism has become a powerful enhancement to the Transformer architecture, which enables models to capture token relationships when encoding positional information. However, the RoPE mechanisms make…

Machine Learning · Computer Science 2026-01-27 Yang Cao , Jiayan Huo , Yingyu Liang , Zhenmei Shi , Zhao Song

This study investigates the existence of positional biases in Transformer-based models for text representation learning, particularly in the context of web document retrieval. We build on previous research that demonstrated loss of…

Information Retrieval · Computer Science 2024-10-29 João Coelho , Bruno Martins , João Magalhães , Jamie Callan , Chenyan Xiong

We propose a new model for learning bilingual word representations from non-parallel document-aligned data. Following the recent advances in word representation learning, our model learns dense real-valued word vectors, that is, bilingual…

Computation and Language · Computer Science 2016-03-01 Ivan Vulić , Marie-Francine Moens

Positional encodings enable Transformers to incorporate sequential information, yet their theoretical understanding remains limited to two properties: distance attenuation and translation invariance. Because natural language lacks purely…

Machine Learning · Computer Science 2026-02-11 Zihan Gu , Ruoyu Chen , Han Zhang , Hua Zhang , Yue Hu

While word embeddings have been shown to implicitly encode various forms of attributional knowledge, the extent to which they capture relational information is far more limited. In previous work, this limitation has been addressed by…

Computation and Language · Computer Science 2019-06-05 Jose Camacho-Collados , Luis Espinosa-Anke , Steven Schockaert

Self-attention relies on positional embeddings to encode input order. Relative Position (RelPos) embeddings are widely used in Automatic Speech Recognition (ASR). However, RelPos has quadratic time complexity to input length and is often…

Computation and Language · Computer Science 2025-06-17 Shucong Zhang , Titouan Parcollet , Rogier van Dalen , Sourav Bhattacharya

Analyses of transformer-based models have shown that they encode a variety of linguistic information from their textual input. While these analyses have shed a light on the relation between linguistic information on one side, and internal…

Computation and Language · Computer Science 2024-07-26 Vivi Nastase , Paola Merlo

Autoregressive language models have demonstrated a remarkable ability to extract latent structure from text. The embeddings from large language models have been shown to capture aspects of the syntax and semantics of language. But what…

Machine Learning · Computer Science 2026-01-09 Liyi Zhang , Michael Y. Li , R. Thomas McCoy , Theodore R. Sumers , Jian-Qiao Zhu , Thomas L. Griffiths

Transformers with causal attention can solve tasks that require positional information without using positional encodings. In this work, we propose and investigate a new hypothesis about how positional information can be stored without…

Computation and Language · Computer Science 2025-01-03 Chunsheng Zuo , Pavel Guerzhoy , Michael Guerzhoy

One of the most remarkable properties of word embeddings is the fact that they capture certain types of semantic and syntactic relationships. Recently, pre-trained language models such as BERT have achieved groundbreaking results across a…

Computation and Language · Computer Science 2019-12-02 Zied Bouraoui , Jose Camacho-Collados , Steven Schockaert

Neural language models learn word representations that capture rich linguistic and conceptual information. Here we investigate the embeddings learned by neural machine translation models. We show that translation-based embeddings outperform…

Computation and Language · Computer Science 2014-11-14 Felix Hill , KyungHyun Cho , Sebastien Jean , Coline Devin , Yoshua Bengio