English
Related papers

Related papers: SesameBERT: Attention for Anywhere

200 papers

We investigate the self-attention mechanism of BERT in a fine-tuning scenario for the classification of scientific articles over a taxonomy of research disciplines. We observe how self-attention focuses on words that are highly related to…

Computation and Language · Computer Science 2021-01-21 Andres Garcia-Silva , Jose Manuel Gomez-Perez

The challenge of fine-grained visual recognition often lies in discovering the key discriminative regions. While such regions can be automatically identified from a large-scale labeled dataset, a similar method might become less effective…

Computer Vision and Pattern Recognition · Computer Science 2022-08-02 Yangyang Shu , Baosheng Yu , Haiming Xu , Lingqiao Liu

Pre-trained contextual language models are ubiquitously employed for language understanding tasks, but are unsuitable for resource-constrained systems. Noncontextual word embeddings are an efficient alternative in these settings. Such…

Computation and Language · Computer Science 2023-04-24 Anik Saha , Alex Gittens , Bulent Yener

Pre-trained language models have shown remarkable results on various NLP tasks. Nevertheless, due to their bulky size and slow inference speed, it is hard to deploy them on edge devices. In this paper, we have a critical insight that…

Computation and Language · Computer Science 2021-09-17 Chenhe Dong , Guangrun Wang , Hang Xu , Jiefeng Peng , Xiaozhe Ren , Xiaodan Liang

Measuring the quality of a generated sequence against a set of references is a central problem in many learning frameworks, be it to compute a score, to assign a reward, or to perform discrimination. Despite great advances in model…

Machine Learning · Computer Science 2020-03-06 Florian Schmidt , Thomas Hofmann

Contextualized entity representations learned by state-of-the-art transformer-based language models (TLMs) like BERT, GPT, T5, etc., leverage the attention mechanism to learn the data context from training data corpus. However, these models…

Computation and Language · Computer Science 2021-09-06 Keyur Faldu , Amit Sheth , Prashant Kikani , Hemang Akbari

Many vision and language models suffer from poor visual grounding - often falling back on easy-to-learn language priors rather than basing their decisions on visual concepts in the image. In this work, we propose a generic approach called…

Computer Vision and Pattern Recognition · Computer Science 2019-10-29 Ramprasaath R. Selvaraju , Stefan Lee , Yilin Shen , Hongxia Jin , Shalini Ghosh , Larry Heck , Dhruv Batra , Devi Parikh

Generated hateful and toxic content by a portion of users in social media is a rising phenomenon that motivated researchers to dedicate substantial efforts to the challenging direction of hateful content identification. We not only need an…

Social and Information Networks · Computer Science 2019-10-29 Marzieh Mozafari , Reza Farahbakhsh , Noel Crespi

Topic segmentation is important in understanding scientific documents since it can not only provide better readability but also facilitate downstream tasks such as information retrieval and question answering by creating appropriate…

Computation and Language · Computer Science 2023-01-06 Jeonghwan Lee , Jiyeong Han , Sunghoon Baek , Min Song

Large, self-supervised transformer-based language representation models have recently received significant amounts of attention, and have produced state-of-the-art results across a variety of tasks simply by scaling up pre-training on…

Computation and Language · Computer Science 2019-10-25 Alexandre Matton , Luke de Oliveira

Document-level machine translation manages to outperform sentence level models by a small margin, but have failed to be widely adopted. We argue that previous research did not make a clear use of the global context, and propose a new…

Computation and Language · Computer Science 2020-09-10 Zaixiang Zheng , Xiang Yue , Shujian Huang , Jiajun Chen , Alexandra Birch

Local feature detection and description play an important role in many computer vision tasks, which are designed to detect and describe keypoints in "any scene" and "any downstream task". Data-driven local feature learning methods need to…

Computer Vision and Pattern Recognition · Computer Science 2025-10-16 Jingqian Wu , Rongtao Xu , Zach Wood-Doughty , Changwei Wang , Shibiao Xu , Edmund Y. Lam

This study presents German FinBERT, a novel pre-trained German language model tailored for financial textual data. The model is trained through a comprehensive pre-training process, leveraging a substantial corpus comprising financial…

Computation and Language · Computer Science 2023-11-16 Moritz Scherrmann

Online continual learning for image classification is crucial for models to adapt to new data while retaining knowledge of previously learned tasks. This capability is essential to address real-world challenges involving dynamic…

Computer Vision and Pattern Recognition · Computer Science 2025-02-14 Adjovi Sim , Zhengkui Wang , Aik Beng Ng , Shalini De Mello , Simon See , Wonmin Byeon

Large pre-trained sentence encoders like BERT start a new chapter in natural language processing. A common practice to apply pre-trained BERT to sequence classification tasks (e.g., classification of sentences or sentence pairs) is by…

Computation and Language · Computer Science 2020-02-26 Wenxuan Zhou , Junyi Du , Xiang Ren

Semantic segmentation is one of the core tasks in the field of computer vision, and its goal is to accurately classify each pixel in an image. The traditional Unet model achieves efficient feature extraction and fusion through an…

Computer Vision and Pattern Recognition · Computer Science 2025-02-07 Xuan Li , Quanchao Lu , Yankaiqi Li , Muqing Li , Yijiashun Qi

Recently, self-attention based models have achieved state-of-the-art performance in sequential recommendation task. Following the custom from language processing, most of these models rely on a simple positional embedding to exploit the…

Machine Learning · Computer Science 2020-08-24 Sung Min Cho , Eunhyeok Park , Sungjoo Yoo

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

Large Language Models (LLMs) exhibit substantial parameter redundancy, particularly in Feed-Forward Networks (FFNs). Existing pruning methods suffer from two primary limitations. First, reliance on dataset-specific calibration introduces…

Computation and Language · Computer Science 2026-02-02 Abhishek Tyagi , Yunuo Cen , Shrey Dhorajiya , Bharadwaj Veeravalli , Xuanyao Fong

We introduce SetBERT, a fine-tuned BERT-based model designed to enhance query embeddings for set operations and Boolean logic queries, such as Intersection (AND), Difference (NOT), and Union (OR). SetBERT significantly improves retrieval…

Computation and Language · Computer Science 2024-06-27 Quan Mai , Susan Gauch , Douglas Adams