English
Related papers

Related papers: Pooling Attention: Evaluating Pretrained Transform…

200 papers

Conventional wisdom suggests that pre-training Vision Transformers (ViT) improves downstream performance by learning useful representations. Is this actually true? We investigate this question and find that the features and representations…

Machine Learning · Computer Science 2024-11-15 Alexander C. Li , Yuandong Tian , Beidi Chen , Deepak Pathak , Xinlei Chen

Recent advances in interpretability suggest we can project weights and hidden states of transformer-based language models (LMs) to their vocabulary, a transformation that makes them more human interpretable. In this paper, we investigate LM…

Computation and Language · Computer Science 2023-11-27 Shahar Katz , Yonatan Belinkov

Transformer-based deep learning models have achieved state-of-the-art performance across numerous language and vision tasks. While the self-attention mechanism, a core component of transformers, has proven capable of handling complex data…

Machine Learning · Computer Science 2025-08-05 Laziz Abdullaev , Tan M. Nguyen

Identifying words that impact a task's performance more than others is a challenge in natural language processing. Transformers models have recently addressed this issue by incorporating an attention mechanism that assigns greater attention…

Computation and Language · Computer Science 2023-03-15 Neşet Özkan Tan , Alex Yuxuan Peng , Joshua Bensemann , Qiming Bao , Tim Hartill , Mark Gahegan , Michael Witbrock

Transformer models have shown impressive performance on a variety of NLP tasks. Off-the-shelf, pre-trained models can be fine-tuned for specific NLP classification tasks, reducing the need for large amounts of additional training data.…

Computation and Language · Computer Science 2020-10-06 Maaike Burghoorn , Maaike H. T. de Boer , Stephan Raaijmakers

Pretrained language models such as BERT, GPT have shown great effectiveness in language understanding. The auxiliary predictive tasks in existing pretraining approaches are mostly defined on tokens, thus may not be able to capture…

Computation and Language · Computer Science 2020-06-19 Hongchao Fang , Sicheng Wang , Meng Zhou , Jiayuan Ding , Pengtao Xie

Transformers are built upon multi-head scaled dot-product attention and positional encoding, which aim to learn the feature representations and token dependencies. In this work, we focus on enhancing the distinctive representation by…

Computer Vision and Pattern Recognition · Computer Science 2022-07-12 Litao Yu , Jian Zhang

The [CLS] token in BERT is commonly used as a fixed-length representation for classification tasks, yet prior work has shown that both other tokens and intermediate layers encode valuable contextual information. In this work, we study…

Computation and Language · Computer Science 2025-10-15 Maike Behrendt , Stefan Sylvius Wagner , Stefan Harmeling

Transformers have recently been utilized to perform object detection and tracking in the context of autonomous driving. One unique characteristic of these models is that attention weights are computed in each forward pass, giving insights…

Computer Vision and Pattern Recognition · Computer Science 2022-10-27 Felicia Ruppel , Florian Faion , Claudius Gläser , Klaus Dietmayer

Transfer entropy (TE) is an information theoretic measure that reveals the directional flow of information between processes, providing valuable insights for a wide range of real-world applications. This work proposes Transfer Entropy…

Information Theory · Computer Science 2025-07-22 Omer Luxembourg , Dor Tsur , Haim Permuter

Despite the significant progress made by transformer models in machine reading comprehension tasks, they still fall short in handling complex reasoning tasks due to the absence of explicit knowledge in the input sequence. To address this…

Computation and Language · Computer Science 2024-01-17 Shima Foolad , Kourosh Kiani

We propose a novel Transformer encoder-based architecture with syntactical knowledge encoded for intent detection and slot filling. Specifically, we encode syntactic knowledge into the Transformer encoder by jointly training it to predict…

Artificial Intelligence · Computer Science 2020-12-23 Jixuan Wang , Kai Wei , Martin Radfar , Weiwei Zhang , Clement Chung

Active learning has been shown to be an effective way to alleviate some of the effort required in utilising large collections of unlabelled data for machine learning tasks without needing to fully label them. The representation mechanism…

Information Retrieval · Computer Science 2020-04-29 Jinghui Lu , Brian MacNamee

Since the popularization of the Transformer as a general-purpose feature encoder for NLP, many studies have attempted to decode linguistic structure from its novel multi-head attention mechanism. However, much of such work focused almost…

Computation and Language · Computer Science 2021-01-27 Vinit Ravishankar , Artur Kulmizev , Mostafa Abdou , Anders Søgaard , Joakim Nivre

The great success of Transformer-based models benefits from the powerful multi-head self-attention mechanism, which learns token dependencies and encodes contextual information from the input. Prior work strives to attribute model decisions…

Computation and Language · Computer Science 2021-02-26 Yaru Hao , Li Dong , Furu Wei , Ke Xu

Self-attention mechanisms model long-range context by using pairwise attention between all input tokens. In doing so, they assume a fixed attention granularity defined by the individual tokens (e.g., text characters or image pixels), which…

Machine Learning · Computer Science 2022-07-06 Chen Huang , Walter Talbott , Navdeep Jaitly , Josh Susskind

Token representation strategies within large-scale neural architectures often rely on contextually refined embeddings, yet conventional approaches seldom encode structured relationships explicitly within token interactions. Self-attention…

Computation and Language · Computer Science 2025-03-27 James Blades , Frederick Somerfield , William Langley , Susan Everingham , Maurice Witherington

Self-attentive neural syntactic parsers using contextualized word embeddings (e.g. ELMo or BERT) currently produce state-of-the-art results in joint parsing and disfluency detection in speech transcripts. Since the contextualized word…

Computation and Language · Computer Science 2020-04-30 Paria Jamshid Lou , Mark Johnson

Interpolation for scattered data is a classical problem in numerical analysis, with a long history of theoretical and practical contributions. Recent advances have utilized deep neural networks to construct interpolators, exhibiting…

Machine Learning · Computer Science 2023-03-15 Shizhe Ding , Boyang Xia , Milong Ren , Dongbo Bu

This paper proposes a novel technique to obtain better downstream ASR performance from a joint encoder-decoder self-supervised model when trained with speech pooled from two different channels (narrow and wide band). The joint…

Audio and Speech Processing · Electrical Eng. & Systems 2023-06-06 Vrunda N. Sukhadia , A. Arunkumar , S. Umesh