English
Related papers

Related papers: Pushdown Layers: Encoding Recursive Structure in T…

200 papers

This research note combines two methods that have recently improved the state of the art in language modeling: Transformers and dynamic evaluation. Transformers use stacked layers of self-attention that allow them to capture long range…

Machine Learning · Computer Science 2019-04-18 Ben Krause , Emmanuel Kahembwe , Iain Murray , Steve Renals

We present a geometric framework for understanding Transformer-based language models, drawing an explicit analogy to General Relativity. Queries and keys induce an effective metric on representation space, and attention acts as a discrete…

Machine Learning · Computer Science 2025-11-06 Riccardo Di Sipio , Jairo Diaz-Rodriguez , Luis Serrano

The Transformer translation model is based on the multi-head attention mechanism, which can be parallelized easily. The multi-head attention network performs the scaled dot-product attention function in parallel, empowering the model by…

Computation and Language · Computer Science 2021-09-13 Hongfei Xu , Qiuhui Liu , Josef van Genabith , Deyi Xiong

Neural attention, especially the self-attention made popular by the Transformer, has become the workhorse of state-of-the-art natural language processing (NLP) models. Very recent work suggests that the self-attention in the Transformer…

Computation and Language · Computer Science 2020-10-16 Zhengxuan Wu , Thanh-Son Nguyen , Desmond C. Ong

Modeling the parser state is key to good performance in transition-based parsing. Recurrent Neural Networks considerably improved the performance of transition-based systems by modelling the global state, e.g. stack-LSTM parsers, or local…

Computation and Language · Computer Science 2020-10-22 Ramon Fernandez Astudillo , Miguel Ballesteros , Tahira Naseem , Austin Blodgett , Radu Florian

Transformers have achieved significant success across various domains, relying on self-attention to capture dependencies. However, the standard first-order attention mechanism is often limited by a low-rank bottleneck, struggling to capture…

Computation and Language · Computer Science 2025-12-05 Hanting Chen , Chong Zhu , Kai Han , Yuchuan Tian , Yuchen Liang , Tianyu Guo , Xinghao Chen , Dacheng Tao , Yunhe Wang

Pairwise dot product-based attention allows Transformers to exchange information between tokens in an input-dependent way, and is key to their success across diverse applications in language and vision. However, a typical Transformer model…

Transformer attention scales quadratically with sequence length O(n^2), limiting long-context use. We propose Adaptive Retention, a probabilistic, layer-wise token selection mechanism that learns which representations to keep under a strict…

Computation and Language · Computer Science 2025-10-13 S M Rafiuddin , Muntaha Nujat Khan

The quadratic complexity of self-attention in Transformer models remains a significant bottleneck for processing long sequences and deploying large language models efficiently. For this approach, there has been significant research into…

Computation and Language · Computer Science 2026-05-26 Spandan Pratyush

Transformers have achieved remarkable success across natural language processing (NLP) and computer vision (CV). However, deep transformer models often suffer from an over-smoothing issue, in which token representations converge to similar…

Machine Learning · Computer Science 2025-10-21 Satoshi Noguchi , Yoshinobu Kawahara

While the Self-Attention mechanism in the Transformer model has proven to be effective in many domains, we observe that it is less effective in more diverse settings (e.g. multimodality) due to the varying granularity of each token and the…

Computer Vision and Pattern Recognition · Computer Science 2024-06-06 Wayner Barrios , SouYoung Jin

The powerful modeling capabilities of all-attention-based transformer architectures often cause overfitting and - for natural language processing tasks - lead to an implicitly learned internal language model in the autoregressive…

Machine Learning · Computer Science 2022-09-21 Timo Lohrenz , Björn Möller , Zhengyang Li , Tim Fingscheidt

Autoregressive (AR) Transformer-based sequence models are known to have difficulty generalizing to sequences longer than those seen during training. When applied to text-to-speech (TTS), these models tend to drop or repeat words or produce…

Computation and Language · Computer Science 2025-03-13 Eric Battenberg , RJ Skerry-Ryan , Daisy Stanton , Soroosh Mariooryad , Matt Shannon , Julian Salazar , David Kao

Structured dropout approaches, such as attention dropout and DropHead, have been investigated to regularize the multi-head attention mechanism in Transformers. In this paper, we propose a new regularization scheme based on token-level…

Computation and Language · Computer Science 2023-10-31 Yangjun Wu , Kebin Fang , Dongxiang Zhang , Han Wang , Hao Zhang , Gang Chen

The conversion from text to speech relies on the accurate mapping from linguistic to acoustic symbol sequences, for which current practice employs recurrent statistical models like recurrent neural networks. Despite the good performance of…

Sound · Computer Science 2018-11-07 Santiago Pascual , Antonio Bonafonte , Joan Serrà

More and more evidence has shown that strengthening layer interactions can enhance the representation power of a deep neural network, while self-attention excels at learning interdependencies by retrieving query-activated information.…

Computer Vision and Pattern Recognition · Computer Science 2023-03-01 Yanwen Fang , Yuxi Cai , Jintai Chen , Jingyu Zhao , Guangjian Tian , Guodong Li

Transformer-based pre-trained language models (PLMs) have dramatically improved the state of the art in NLP across many tasks. This has led to substantial interest in analyzing the syntactic knowledge PLMs learn. Previous approaches to this…

Computation and Language · Computer Science 2020-10-20 Bowen Li , Taeuk Kim , Reinald Kim Amplayo , Frank Keller

Attention mechanisms have improved the performance of NLP tasks while allowing models to remain explainable. Self-attention is currently widely used, however interpretability is difficult due to the numerous attention distributions. Recent…

Computation and Language · Computer Science 2020-10-30 Khalil Mrini , Franck Dernoncourt , Quan Tran , Trung Bui , Walter Chang , Ndapa Nakashole

Standard Transformers have a fixed computational depth, fundamentally limiting their ability to generalize to tasks requiring variable-depth reasoning, such as multi-hop graph traversal or nested logic. We propose a depth-recurrent…

Machine Learning · Computer Science 2026-03-24 Hung-Hsuan Chen

Large Language Models (LLMs) have achieved impressive performance across diverse tasks but continue to struggle with learning transitive relations, a cornerstone for complex planning. To address this issue, we investigate the Multi-Token…

Artificial Intelligence · Computer Science 2025-09-30 Qimin Zhong , Hao Liao , Siwei Wang , Mingyang Zhou , Xiaoqun Wu , Rui Mao , Wei Chen