English
Related papers

Related papers: Efficient Long Sequence Encoding via Synchronizati…

200 papers

Generative models for dialog systems have gained much interest because of the recent success of RNN and Transformer based models in tasks like question answering and summarization. Although the task of dialog response generation is…

Computation and Language · Computer Science 2021-05-11 Bishal Santra , Potnuru Anusha , Pawan Goyal

Transformers achieve unrivalled performance in modelling language, but remain inefficient in terms of memory and time complexity. A possible remedy is to reduce the sequence length in the intermediate layers by pooling fixed-length segments…

Computation and Language · Computer Science 2023-10-25 Piotr Nawrot , Jan Chorowski , Adrian Łańcucki , Edoardo M. Ponti

Hybrid sequence models that combine efficient Transformer components with linear sequence modeling blocks are a promising alternative to pure Transformers, but most are still pretrained from scratch and therefore fail to reuse existing…

While large pretrained Transformer models have proven highly capable at tackling natural language tasks, handling long sequence inputs continues to be a significant challenge. One such task is long input summarization, where inputs are…

Computation and Language · Computer Science 2022-08-10 Jason Phang , Yao Zhao , Peter J. Liu

Transformer models cannot easily scale to long sequences due to their O(N^2) time and space complexity. This has led to Transformer variants seeking to lower computational complexity, such as Longformer and Performer. While such models have…

Computation and Language · Computer Science 2024-12-10 Guanghui Qin , Yukun Feng , Benjamin Van Durme

In this paper, we develop a neural summarization model which can effectively process multiple input documents and distill Transformer architecture with the ability to encode documents in a hierarchical manner. We represent cross-document…

Computation and Language · Computer Science 2019-05-31 Yang Liu , Mirella Lapata

Transformer is important for text modeling. However, it has difficulty in handling long documents due to the quadratic complexity with input text length. In order to handle this problem, we propose a hierarchical interactive Transformer…

Computation and Language · Computer Science 2021-12-10 Chuhan Wu , Fangzhao Wu , Tao Qi , Yongfeng Huang

Most of modern neural machine translation (NMT) models are based on an encoder-decoder framework with an attention mechanism. While they perform well on standard datasets, they can have trouble in translation of long inputs that are rare or…

Computation and Language · Computer Science 2026-03-31 Shuhei Kondo , Katsuhito Sudoh , Yuji Matsumoto

With the rapid advancement of Neural Machine Translation (NMT), enhancing translation efficiency and quality has become a focal point of research. Despite the commendable performance of general models such as the Transformer in various…

Computation and Language · Computer Science 2024-02-26 Jingpu Yang , Zehua Han , Mengyu Xiang , Helin Wang , Yuxiao Huang , Miao Fang

The task of learning to map an input set onto a permuted sequence of its elements is challenging for neural networks. Set-to-sequence problems occur in natural language processing, computer vision and structure prediction, where…

Machine Learning · Computer Science 2022-06-09 Mateusz Jurewicz , Leon Derczynski

Since its introduction, the transformers architecture has seen great adoption in NLP applications, but it also has limitations. Although the self-attention mechanism allows for generating very rich representations of the input text, its…

Computation and Language · Computer Science 2023-11-10 Daniele Giofré , Sneha Ghantasala

The capabilities of transformer networks such as ChatGPT and other Large Language Models (LLMs) have captured the world's attention. The crucial computational mechanism underlying their performance relies on transforming a complete input…

Computation and Language · Computer Science 2024-08-19 Lyle Muller , Patricia S. Churchland , Terrence J. Sejnowski

The attention mechanisms are playing a boosting role in advancements in sequence-to-sequence problems. Transformer architecture achieved new state of the art results in machine translation, and it's variants are since being introduced in…

Machine Learning · Computer Science 2020-05-12 Abhishek Niranjan , M Ali Basha Shaik , Kushal Verma

Program synthesis aims to automatically construct human-readable programs that satisfy given task specifications, such as input/output pairs or demonstrations. Recent works have demonstrated encouraging results in a variety of domains, such…

Software Engineering · Computer Science 2023-03-13 Linghan Zhong , Ryan Lindeborg , Jesse Zhang , Joseph J. Lim , Shao-Hua Sun

Text embeddings from Large Language Models (LLMs) have become foundational for numerous applications. However, these models typically operate on raw text, overlooking the rich structural information, such as hyperlinks or citations, that…

Machine Learning · Computer Science 2025-10-13 Shikun Liu , Haoyu Wang , Mufei Li , Pan Li

This study reports an unintuitive finding that positional encoding enhances learning of recurrent neural networks (RNNs). Positional encoding is a high-dimensional representation of time indices on input data. Most famously, positional…

Machine Learning · Computer Science 2024-11-28 Takashi Morita

In recent years, the sequence-to-sequence learning neural networks with attention mechanism have achieved great progress. However, there are still challenges, especially for Neural Machine Translation (NMT), such as lower translation…

Computation and Language · Computer Science 2018-11-26 Si Zuo , Zhimin Xu

Transformer-based models have achieved state-of-the-art results in a wide range of natural language processing (NLP) tasks including document summarization. Typically these systems are trained by fine-tuning a large pre-trained model to the…

Computation and Language · Computer Science 2021-06-01 Potsawee Manakul , Mark J. F. Gales

Transformer network architecture has proven effective in speech enhancement. However, as its core module, self-attention suffers from quadratic complexity, making it infeasible for training on long speech utterances. In practical scenarios,…

Audio and Speech Processing · Electrical Eng. & Systems 2025-06-10 Qiquan Zhang , Hongxu Zhu , Xinyuan Qian , Eliathamby Ambikairajah , Haizhou Li

Analyzing long text data such as customer call transcripts is a cost-intensive and tedious task. Machine learning methods, namely Transformers, are leveraged to model agent-customer interactions. Unfortunately, Transformers adhere to…

Computation and Language · Computer Science 2025-02-19 Annamalai Senthilnathan , Kristjan Arumae , Mohammed Khalilia , Zhengzheng Xing , Aaron R. Colak