English
Related papers

Related papers: Can Model Fusing Help Transformers in Long Documen…

200 papers

Lifelong learning has recently attracted attention in building machine learning systems that continually accumulate and transfer knowledge to help future learning. Unsupervised topic modeling has been popularly used to discover topics from…

Computation and Language · Computer Science 2023-06-28 Pankaj Gupta , Yatin Chaudhary , Thomas Runkler , Hinrich Schütze

Embedding fusion has emerged as an effective approach for enhancing performance across various NLP tasks. However, systematic guidelines for selecting optimal layers and developing effective fusion strategies for the integration of LLMs…

Computation and Language · Computer Science 2025-04-09 Jiho Gwak , Yuchul Jung

Recent approaches in literature have exploited the multi-modal information in documents (text, layout, image) to serve specific downstream document tasks. However, they are limited by their - (i) inability to learn cross-modal…

Computation and Language · Computer Science 2022-01-06 Subhojeet Pramanik , Shashank Mujumdar , Hima Patel

Encoding long sequences in Natural Language Processing (NLP) is a challenging problem. Though recent pretraining language models achieve satisfying performances in many NLP tasks, they are still restricted by a pre-defined maximum length,…

Computation and Language · Computer Science 2023-05-16 Irene Li , Aosong Feng , Dragomir Radev , Rex Ying

Most approaches for similar text retrieval and ranking with long natural language queries rely at some level on queries and responses having words in common with each other. Recent applications of transformer-based neural language models to…

Information Retrieval · Computer Science 2020-05-22 Javed Qadrud-Din , Ashraf Bah Rabiou , Ryan Walker , Ravi Soni , Martin Gajek , Gabriel Pack , Akhil Rangaraj

In this paper we perform a comparative analysis of three models for feature representation of text documents in the context of document classification. In particular, we consider the most often used family of models bag-of-words, recently…

Computation and Language · Computer Science 2017-07-06 Sanda Martinčić-Ipšić , Tanja Miličić , Ljupčo Todorovski

Pretrained transformer-based Language Models (LMs) are well-known for their ability to achieve significant improvement on NLP tasks, but their black-box nature, which leads to a lack of interpretability, has been a major concern. My…

Computation and Language · Computer Science 2024-12-06 Ximing Wen

Despite the known limitations, most machine translation systems today still operate on the sentence-level. One reason for this is, that most parallel training data is only sentence-level aligned, without document-level meta information…

Computation and Language · Computer Science 2023-10-20 Frithjof Petrick , Christian Herold , Pavel Petrushkov , Shahram Khadivi , Hermann Ney

Natural Language Processing (NLP) is an important branch of artificial intelligence that studies how to enable computers to understand, process, and generate human language. Text classification is a fundamental task in NLP, which aims to…

Computation and Language · Computer Science 2024-03-18 Xiaonan Xu , Zheng Xu , Zhipeng Ling , Zhengyu Jin , ShuQian Du

Time, cost, and energy efficiency are critical considerations in Deep-Learning (DL), particularly when processing long texts. Transformers, which represent the current state of the art, exhibit quadratic computational complexity relative to…

Computation and Language · Computer Science 2025-07-11 Fardin Rastakhiz

Effective training of today's large language models (LLMs) depends on large batches and long sequences for throughput and accuracy. To handle variable-length sequences on hardware accelerators, it is common practice to introduce padding…

Computation and Language · Computer Science 2022-10-07 Mario Michael Krell , Matej Kosec , Sergio P. Perez , Andrew Fitzgibbon

Transformer-based Large Language Models (LLMs) have been applied in diverse areas such as knowledge bases, human interfaces, and dynamic agents, and marking a stride towards achieving Artificial General Intelligence (AGI). However, current…

Computation and Language · Computer Science 2024-02-27 Yunpeng Huang , Jingwei Xu , Junyu Lai , Zixu Jiang , Taolue Chen , Zenan Li , Yuan Yao , Xiaoxing Ma , Lijuan Yang , Hao Chen , Shupeng Li , Penghao Zhao

Word representation has always been an important research area in the history of natural language processing (NLP). Understanding such complex text data is imperative, given that it is rich in information and can be used widely across…

Computation and Language · Computer Science 2020-11-10 Usman Naseem , Imran Razzak , Shah Khalid Khan , Mukesh Prasad

Text classification is fundamental in natural language processing (NLP), and Graph Neural Networks (GNN) are recently applied in this task. However, the existing graph-based works can neither capture the contextual word relationships within…

Computation and Language · Computer Science 2020-05-13 Yufeng Zhang , Xueli Yu , Zeyu Cui , Shu Wu , Zhongzhen Wen , Liang Wang

Long context inference scenarios have become increasingly important for large language models, yet they introduce significant computational latency. While prior research has optimized long-sequence inference through operators, model…

Computation and Language · Computer Science 2025-11-10 Wei Shao , Lingchao Zheng , Pengyu Wang , Peizhen Zheng , Jun Li , Yuwei Fan

Inductive transfer learning has greatly impacted computer vision, but existing approaches in NLP still require task-specific modifications and training from scratch. We propose Universal Language Model Fine-tuning (ULMFiT), an effective…

Computation and Language · Computer Science 2018-05-24 Jeremy Howard , Sebastian Ruder

Recent advancements in Natural Language Processing (NLP) have fostered the development of Large Language Models (LLMs) that can solve an immense variety of tasks. One of the key aspects of their application is their ability to work with…

Computation and Language · Computer Science 2024-08-06 Igor Churin , Murat Apishev , Maria Tikhonova , Denis Shevelev , Aydar Bulatov , Yuri Kuratov , Sergej Averkiev , Alena Fenogenova

Text segmentation is important for signaling a document's structure. Without segmenting a long document into topically coherent sections, it is difficult for readers to comprehend the text, let alone find important information. The problem…

Computation and Language · Computer Science 2022-11-01 Sangwoo Cho , Kaiqiang Song , Xiaoyang Wang , Fei Liu , Dong Yu

Semi-supervised learning through deep generative models and multi-lingual pretraining techniques have orchestrated tremendous success across different areas of NLP. Nonetheless, their development has happened in isolation, while the…

Computation and Language · Computer Science 2021-01-27 Yi Zhu , Ehsan Shareghi , Yingzhen Li , Roi Reichart , Anna Korhonen

This research conducts a comparative study on multilingual text classification methods, utilizing deep learning and embedding visualization. The study employs LangDetect, LangId, FastText, and Sentence Transformer on a dataset encompassing…

Computation and Language · Computer Science 2023-12-08 Arinjay Wyawhare