English
Related papers

Related papers: Efficient Attentions for Long Document Summarizati…

200 papers

Scaling language models to handle longer input sequences typically necessitates large key-value (KV) caches, resulting in substantial memory overhead during inference. In this paper, we propose Tensor Product Attention (TPA), a novel…

Computation and Language · Computer Science 2026-01-13 Yifan Zhang , Yifeng Liu , Huizhuo Yuan , Zhen Qin , Yang Yuan , Quanquan Gu , Andrew Chi-Chih Yao

Length extrapolation algorithms based on Rotary position embedding (RoPE) have shown promising results in extending the context length of language models. However, understanding how position embedding can capture longer-range contextual…

Computation and Language · Computer Science 2024-10-22 Xiangyu Hong , Che Jiang , Biqing Qi , Fandong Meng , Mo Yu , Bowen Zhou , Jie Zhou

Pretrained transformer models have demonstrated remarkable performance across various natural language processing tasks. These models leverage the attention mechanism to capture long- and short-range dependencies in the sequence. However,…

Computation and Language · Computer Science 2023-10-20 Qingru Zhang , Dhananjay Ram , Cole Hawkins , Sheng Zha , Tuo Zhao

Efficient attention mechanisms enable long-context transformers but often miss globally important tokens, degrading modeling quality. We introduce a pre-scoring framework that assigns a query-independent global importance prior to keys…

Machine Learning · Computer Science 2026-02-10 Zhexiang Li , Haoyu Wang , Yutong Bao , David Woodruff

Recent studies have demonstrated the effectiveness of position encoding in transformer architectures. By incorporating positional information, this approach provides essential guidance for modeling dependencies between elements across…

Machine Learning · Computer Science 2025-08-27 Avinash Amballa

We propose a novel end-to-end document understanding model called SeRum (SElective Region Understanding Model) for extracting meaningful information from document images, including document analysis, retrieval, and office automation. Unlike…

Computer Vision and Pattern Recognition · Computer Science 2023-09-06 Haoyu Cao , Changcun Bao , Chaohu Liu , Huang Chen , Kun Yin , Hao Liu , Yinsong Liu , Deqiang Jiang , Xing Sun

Attention mechanism plays a dominant role in the sequence generation models and has been used to improve the performance of machine translation and abstractive text summarization. Different from neural machine translation, in the task of…

Computation and Language · Computer Science 2020-04-09 Piji Li , Lidong Bing , Zhongyu Wei , Wai Lam

Document-level relation extraction typically relies on text-based encoders and hand-coded pooling heuristics to aggregate information learned by the encoder. In this paper, we leverage the intrinsic graph processing capabilities of the…

Computation and Language · Computer Science 2024-08-07 Andrei C. Coman , Christos Theodoropoulos , Marie-Francine Moens , James Henderson

Transformer models have achieved remarkable results in a wide range of applications. However, their scalability is hampered by the quadratic time and memory complexity of the self-attention mechanism concerning the sequence length. This…

Machine Learning · Computer Science 2024-02-27 Yury Nahshan , Joseph Kampeas , Emir Haleva

Large language models with long context windows can answer complex questions directly from full-length academic, technical, and policy documents, but passing entire documents is often costly, slow, and can degrade answer quality while…

The utilization of Transformer-based models prospers the growth of multi-document summarization (MDS). Given the huge impact and widespread adoption of Transformer-based models in various natural language processing tasks, investigating…

Computation and Language · Computer Science 2024-07-17 Congbo Ma , Wei Emma Zhang , Dileepa Pitawela , Haojie Zhuang , Yanfeng Shu

In the Transformer model, "self-attention" combines information from attended embeddings into the representation of the focal embedding in the next layer. Thus, across layers of the Transformer, information originating from different tokens…

Machine Learning · Computer Science 2020-06-02 Samira Abnar , Willem Zuidema

Recent advances in deep learning have relied heavily on the use of large Transformers due to their ability to learn at scale. However, the core building block of Transformers, the attention operator, exhibits quadratic cost in sequence…

In this work, we model abstractive text summarization using Attentional Encoder-Decoder Recurrent Neural Networks, and show that they achieve state-of-the-art performance on two different corpora. We propose several novel models that…

Computation and Language · Computer Science 2016-08-29 Ramesh Nallapati , Bowen Zhou , Cicero Nogueira dos santos , Caglar Gulcehre , Bing Xiang

Latest development of neural models has connected the encoder and decoder through a self-attention mechanism. In particular, Transformer, which is solely based on self-attention, has led to breakthroughs in Natural Language Processing (NLP)…

Computation and Language · Computer Science 2019-11-07 Xindian Ma , Peng Zhang , Shuai Zhang , Nan Duan , Yuexian Hou , Dawei Song , Ming Zhou

As the demand for processing extended textual data grows, the ability to handle long-range dependencies and maintain computational efficiency is more critical than ever. One of the key issues for long-sequence modeling using attention-based…

Computation and Language · Computer Science 2025-05-26 Aosong Feng , Rex Ying , Leandros Tassiulas

Many NLP tasks require processing long contexts beyond the length limit of pretrained models. In order to scale these models to longer text sequences, many efficient long-range attention variants have been proposed. Despite the abundance of…

Computation and Language · Computer Science 2022-05-05 Wenhan Xiong , Barlas Oğuz , Anchit Gupta , Xilun Chen , Diana Liskovich , Omer Levy , Wen-tau Yih , Yashar Mehdad

This paper addresses the problem of supervised video summarization by formulating it as a sequence-to-sequence learning problem, where the input is a sequence of original video frames, the output is a keyshot sequence. Our key idea is to…

Computer Vision and Pattern Recognition · Computer Science 2018-04-17 Zhong Ji , Kailin Xiong , Yanwei Pang , Xuelong Li

The long-context capability of recent large transformer models can be surmised to rely on techniques such as attention/model parallelism, as well as hardware-level optimizations. While these strategies allow input lengths to scale to…

Computer Vision and Pattern Recognition · Computer Science 2025-07-28 Toufiq Parag , Ahmed Elgammal

Long-sequence transformers are designed to improve the representation of longer texts by language models and their performance on downstream document-level tasks. However, not much is understood about the quality of token-level predictions…

Computation and Language · Computer Science 2023-03-15 Kamil Bujel , Andrew Caines , Helen Yannakoudakis , Marek Rei