English
Related papers

Related papers: What Do Position Embeddings Learn? An Empirical St…

200 papers

We investigate how embedding dimension affects the emergence of an internal "world model" in a transformer trained with reinforcement learning to perform bubble-sort-style adjacent swaps. Models achieve high accuracy even with very small…

Machine Learning · Computer Science 2025-10-22 Brady Bhalla , Honglu Fan , Nancy Chen , Tony Yue YU

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

Pre-trained transformer language models (LMs) have in recent years become the dominant paradigm in applied NLP. These models have achieved state-of-the-art performance on tasks such as information extraction, question answering, sentiment…

Computation and Language · Computer Science 2025-04-14 Aidan Mannion , Thierry Chevalier , Didier Schwab , Lorraine Geouriot

Positional bias - where models overemphasize certain positions regardless of content - has been shown to negatively impact model performance across various tasks. While recent research has extensively examined positional bias in text…

Computer Vision and Pattern Recognition · Computer Science 2025-11-17 Kebin Wu , Fatima Albreiki

Transformer-based Large Language Models (LLMs) have revolutionized Natural Language Processing by demonstrating exceptional performance across diverse tasks. This study investigates the impact of the parameter initialization scale on the…

Computation and Language · Computer Science 2025-05-22 Junjie Yao , Zhongwang Zhang , Zhi-Qin John Xu

Without positional information, attention-based Transformer neural networks are permutation-invariant. Absolute or relative positional embeddings are the most popular ways to feed Transformer models with positional information. Absolute…

Machine Learning · Computer Science 2021-11-10 Tatiana Likhomanenko , Qiantong Xu , Gabriel Synnaeve , Ronan Collobert , Alex Rogozhnikov

Transformers are neural networks that revolutionized natural language processing and machine learning. They process sequences of inputs, like words, using a mechanism called self-attention, which is trained via masked language modeling…

Disordered Systems and Neural Networks · Physics 2024-04-17 Riccardo Rende , Federica Gerace , Alessandro Laio , Sebastian Goldt

Recently, the emergence of pre-trained models (PTMs) has brought natural language processing (NLP) to a new era. In this survey, we provide a comprehensive review of PTMs for NLP. We first briefly introduce language representation learning…

Computation and Language · Computer Science 2021-06-24 Xipeng Qiu , Tianxiang Sun , Yige Xu , Yunfan Shao , Ning Dai , Xuanjing Huang

While one of the first steps in many NLP systems is selecting what pre-trained word embeddings to use, we argue that such a step is better left for neural networks to figure out by themselves. To that end, we introduce dynamic…

Computation and Language · Computer Science 2018-09-06 Douwe Kiela , Changhan Wang , Kyunghyun Cho

Transfer learning, where a model is first pre-trained on a data-rich task before being fine-tuned on a downstream task, has emerged as a powerful technique in natural language processing (NLP). The effectiveness of transfer learning has…

Machine Learning · Computer Science 2023-09-20 Colin Raffel , Noam Shazeer , Adam Roberts , Katherine Lee , Sharan Narang , Michael Matena , Yanqi Zhou , Wei Li , Peter J. Liu

Cross-lingual word embeddings are becoming increasingly important in multilingual NLP. Recently, it has been shown that these embeddings can be effectively learned by aligning two disjoint monolingual vector spaces through linear…

Computation and Language · Computer Science 2018-08-28 Yerai Doval , Jose Camacho-Collados , Luis Espinosa-Anke , Steven Schockaert

We propose a promising neural network model with which to acquire a grounded representation of robot actions and the linguistic descriptions thereof. Properly responding to various linguistic expressions, including polysemous words, is an…

Robotics · Computer Science 2021-04-20 Minori Toyoda , Kanata Suzuki , Hiroki Mori , Yoshihiko Hayashi , Tetsuya Ogata

Pre-trained language models are effective in a variety of natural language tasks, but it has been argued their capabilities fall short of fully learning meaning or understanding language. To understand the extent to which language models…

Software Engineering · Computer Science 2024-02-29 Toufique Ahmed , Dian Yu , Chengxuan Huang , Cathy Wang , Prem Devanbu , Kenji Sagae

Applying machine learning to tasks that operate with code changes requires their numerical representation. In this work, we propose an approach for obtaining such representations during pre-training and evaluate them on two different…

Software Engineering · Computer Science 2021-07-12 Mikhail Pravilov , Egor Bogomolov , Yaroslav Golubev , Timofey Bryksin

Deep transformer models have pushed performance on NLP tasks to new limits, suggesting sophisticated treatment of complex linguistic inputs, such as phrases. However, we have limited understanding of how these models handle representation…

Computation and Language · Computer Science 2020-10-15 Lang Yu , Allyson Ettinger

How do transformer language models memorize factual associations? A common view casts internal weight matrices as associative memories over pairs of embeddings, requiring parameter counts that scale linearly with the number of facts. We…

Computation and Language · Computer Science 2026-05-13 Shauli Ravfogel , Gilad Yehudai , Joan Bruna , Alberto Bietti

Transformer-based pretrained language models (T-PTLMs) have achieved great success in almost every NLP task. The evolution of these models started with GPT and BERT. These models are built on the top of transformers, self-supervised…

Computation and Language · Computer Science 2021-08-31 Katikapalli Subramanyam Kalyan , Ajit Rajasekharan , Sivanesan Sangeetha

Natural language processing for document scans and PDFs has the potential to enormously improve the efficiency of business processes. Layout-aware word embeddings such as LayoutLM have shown promise for classification of and information…

Computation and Language · Computer Science 2021-09-02 Anik Saha , Catherine Finegan-Dollak , Ashish Verma

Despite exceptional capabilities in knowledge-intensive tasks, Large Language Models (LLMs) face a critical gap in understanding how they internalize new knowledge, particularly how to structurally embed acquired knowledge in their neural…

Machine Learning · Computer Science 2025-06-03 Yixin Ou , Yunzhi Yao , Ningyu Zhang , Hui Jin , Jiacheng Sun , Shumin Deng , Zhenguo Li , Huajun Chen

Transformers have impressive generalization capabilities on tasks with a fixed context length. However, they fail to generalize to sequences of arbitrary length, even for seemingly simple tasks such as duplicating a string. Moreover, simply…