English
Related papers

Related papers: The Double Helix inside the NLP Transformer

200 papers

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

Large language models (LLMs) have shown an impressive ability to perform tasks believed to require thought processes. When the model does not document an explicit thought process, it becomes difficult to understand the processes occurring…

Computation and Language · Computer Science 2024-06-21 Yuval Shalev , Amir Feder , Ariel Goldstein

The question of what kinds of linguistic information are encoded in different layers of Transformer-based language models is of considerable interest for the NLP community. Existing work, however, has overwhelmingly focused on word-level…

Computation and Language · Computer Science 2023-10-19 Dmitry Nikolaev , Sebastian Padó

Numerical interactions leading to users sharing textual content published by others are naturally represented by a network where the individuals are associated with the nodes and the exchanged texts with the edges. To understand those…

Machine Learning · Computer Science 2024-02-14 Rémi Boutin , Pierre Latouche , Charles Bouveyron

Positional encoding (PE) underpins how permutation-invariant Transformers represent sequence order, yet how positional information is processed and stored remains poorly understood. Modern PE methods such as RoPE still struggle on tasks…

Computation and Language · Computer Science 2026-05-29 Pierre-Antoine Lequeu , Camille Barboule , Benjamin Piwowarski

We study how syntactic and semantic information is encoded in inner layer representations of Large Language Models (LLMs), focusing on the very large DeepSeek-V3. We find that, by averaging hidden-representation vectors of sentences sharing…

Computation and Language · Computer Science 2026-05-29 Santiago Acevedo , Alessandro Laio , Marco Baroni

Distributional semantics based on neural approaches is a cornerstone of Natural Language Processing, with surprising connections to human meaning representation as well. Recent Transformer-based Language Models have proven capable of…

Computation and Language · Computer Science 2022-04-04 Daniel Loureiro , Alípio Mário Jorge , Jose Camacho-Collados

Lexical ambiguity can impede NLP systems from accurate understanding of semantics. Despite its potential benefits, the integration of sense-level information into NLP systems has remained understudied. By incorporating a novel…

Computation and Language · Computer Science 2017-10-19 Mohammad Taher Pilehvar , Jose Camacho-Collados , Roberto Navigli , Nigel Collier

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

We study the challenging problem for inference tasks on large-scale graph datasets of Graph Neural Networks: huge time and memory consumption, and try to overcome it by reducing reliance on graph structure. Even though distilling graph…

Machine Learning · Computer Science 2024-03-05 Junxian Li , Bin Shi , Erfei Cui , Hua Wei , Qinghua Zheng

Deep learning methods employ multiple processing layers to learn hierarchical representations of data and have produced state-of-the-art results in many domains. Recently, a variety of model designs and methods have blossomed in the context…

Computation and Language · Computer Science 2018-11-27 Tom Young , Devamanyu Hazarika , Soujanya Poria , Erik Cambria

Traditional representations like Bag of words are high dimensional, sparse and ignore the order as well as syntactic and semantic information. Distributed vector representations or embeddings map variable length text to dense fixed length…

Computation and Language · Computer Science 2020-11-26 Kalyan KS , S Sangeetha

Low-dimensional embeddings are a cornerstone in the modelling and analysis of complex networks. However, most existing approaches for mining network embedding spaces rely on computationally intensive machine learning systems to facilitate…

Social and Information Networks · Computer Science 2024-10-04 Alexandros Xenos , Noel-Malod Dognin , Natasa Przulj

In the context of classification problems, Deep Learning (DL) approaches represent state of art. Many DL approaches are based on variations of standard multi-layer feed-forward neural networks. These are also referred to as deep networks.…

Machine Learning · Computer Science 2023-11-21 Andrea Apicella , Francesco Isgrò , Roberto Prevete

Word embeddings are rich word representations, which in combination with deep neural networks, lead to large performance gains for many NLP tasks. However, word embeddings are represented by dense, real-valued vectors and they are therefore…

Computation and Language · Computer Science 2019-12-24 Andreas Hanselowski , Iryna Gurevych

Sentence embeddings are central to modern NLP and AI systems, yet little is known about their internal structure. While we can compare these embeddings using measures such as cosine similarity, the contributing features are not…

Computation and Language · Computer Science 2025-06-11 Matthieu Tehenan , Vikram Natarajan , Jonathan Michala , Milton Lin , Juri Opitz

Sentence and word embeddings encode structural and semantic information in a distributed manner. Part of the information encoded -- particularly lexical information -- can be seen as continuous, whereas other -- like structural information…

Computation and Language · Computer Science 2023-12-19 Vivi Nastase , Paola Merlo

Contextual word embeddings obtained from pre-trained language model (PLM) have proven effective for various natural language processing tasks at the word level. However, interpreting the hidden aspects within embeddings, such as syntax and…

Computation and Language · Computer Science 2023-10-10 Nayoung Choi

Transformer layers, which use an alternating pattern of multi-head attention and multi-layer perceptron (MLP) layers, provide an effective tool for a variety of machine learning problems. As the transformer layers use residual connections…

Machine Learning · Computer Science 2022-12-13 Yaofeng Desmond Zhong , Tongtao Zhang , Amit Chakraborty , Biswadip Dey

The adaptation of pretrained language models to solve supervised tasks has become a baseline in NLP, and many recent works have focused on studying how linguistic information is encoded in the pretrained sentence representations. Among…

Computation and Language · Computer Science 2021-02-11 Laura Pérez-Mayos , Roberto Carlini , Miguel Ballesteros , Leo Wanner
‹ Prev 1 2 3 10 Next ›