English
Related papers

Related papers: Hierarchical Neural Network Approaches for Long Do…

200 papers

Deep learning approaches are superior in NLP due to their ability to extract informative features and patterns from languages. The two most successful neural architectures are LSTM and transformers, used in large pretrained language models…

Computation and Language · Computer Science 2022-03-03 Matej Klemen , Luka Krsnik , Marko Robnik-Šikonja

The Sentence-State LSTM (S-LSTM) is a powerful and high efficient graph recurrent network, which views words as nodes and performs layer-wise recurrent steps between them simultaneously. Despite its successes on text representations, the…

Computation and Language · Computer Science 2020-03-03 Yijin Liu , Fandong Meng , Yufeng Chen , Jinan Xu , Jie Zhou

This paper presents the novel way combining the BERT embedding method and the graph convolutional neural network. This combination is employed to solve the text classification problem. Initially, we apply the BERT embedding method to the…

Computation and Language · Computer Science 2022-09-07 Loc Hoang Tran , Tuan Tran , An Mai

Deceptive text classification is a critical task in natural language processing that aims to identify deceptive o fraudulent content. This study presents a comparative analysis of machine learning and transformer-based approaches for…

Computation and Language · Computer Science 2023-08-14 Anusuya Krishnan

Text summarization aims to condense long documents and retain key information. Critical to the success of a summarization model is the faithful inference of latent representations of words or tokens in the source documents. Most recent…

Computation and Language · Computer Science 2022-03-16 Bo Pang , Erik Nijkamp , Wojciech Kryściński , Silvio Savarese , Yingbo Zhou , Caiming Xiong

Although BERT is widely used by the NLP community, little is known about its inner workings. Several attempts have been made to shed light on certain aspects of BERT, often with contradicting conclusions. A much raised concern focuses on…

Computation and Language · Computer Science 2020-10-13 Nikolaos Manginas , Ilias Chalkidis , Prodromos Malakasiotis

Document classification tasks were primarily tackled at word level. Recent research that works with character-level inputs shows several benefits over word-level approaches such as natural incorporation of morphemes and better handling of…

Computation and Language · Computer Science 2016-02-02 Yijun Xiao , Kyunghyun Cho

Transformer architectures have achieved state-of-the-art performance across natural language tasks, yet they fundamentally misrepresent the hierarchical nature of human language by processing text as flat token sequences. This results in…

Computation and Language · Computer Science 2025-09-26 Ayan Sar , Sampurna Roy , Kanav Gupta , Anurag Kaushish , Tanupriya Choudhury , Abhijit Kumar

Pre-trained Transformers currently dominate most NLP tasks. They impose, however, limits on the maximum input length (512 sub-words in BERT), which are too restrictive in the legal domain. Even sparse-attention models, such as Longformer…

Computation and Language · Computer Science 2022-11-11 Dimitris Mamakas , Petros Tsotsi , Ion Androutsopoulos , Ilias Chalkidis

Transformer has been applied in the field of computer vision due to its excellent performance in natural language processing, surpassing traditional convolutional neural networks and achieving new state-of-the-art. ViT divides an image into…

Computer Vision and Pattern Recognition · Computer Science 2024-04-23 Yuang Liu , Zhiheng Qiu , Xiaokai Qin

How and to what extent does BERT encode syntactically-sensitive hierarchical information or positionally-sensitive linear information? Recent work has shown that contextual representations like BERT perform well on tasks that require…

Computation and Language · Computer Science 2019-06-06 Yongjie Lin , Yi Chern Tan , Robert Frank

The key to the text classification task is language representation and important information extraction, and there are many related studies. In recent years, the research on graph neural network (GNN) in text classification has gradually…

Computation and Language · Computer Science 2022-09-16 Shuai Hua , Xinxin Li , Yunpeng Jing , Qunfeng Liu

In this paper, we study machine reading comprehension (MRC) on long texts, where a model takes as inputs a lengthy document and a question and then extracts a text span from the document as an answer. State-of-the-art models tend to use a…

Computation and Language · Computer Science 2020-05-20 Hongyu Gong , Yelong Shen , Dian Yu , Jianshu Chen , Dong Yu

Since automatic translations can contain errors that require substantial human post-editing, machine translation proofreading is essential for improving quality. This paper proposes a novel hybrid approach for robust proofreading that…

Computation and Language · Computer Science 2025-06-06 Feijun Liu , Huifeng Wang , Kun Wang , Yizhen Wang

Neural extractive summarization models usually employ a hierarchical encoder for document encoding and they are trained using sentence-level labels, which are created heuristically using rule-based methods. Training the hierarchical encoder…

Computation and Language · Computer Science 2019-05-17 Xingxing Zhang , Furu Wei , Ming Zhou

Transformer architectures show significant promise for natural language processing. Given that a single pretrained model can be fine-tuned to perform well on many different tasks, these networks appear to extract generally useful linguistic…

Machine Learning · Computer Science 2019-10-29 Andy Coenen , Emily Reif , Ann Yuan , Been Kim , Adam Pearce , Fernanda Viégas , Martin Wattenberg

Recently, the development of pre-trained language models has brought natural language processing (NLP) tasks to the new state-of-the-art. In this paper we explore the efficiency of various pre-trained language models. We pre-train a list of…

Computation and Language · Computer Science 2023-07-27 Tong Guo

The Transformer architecture is superior to RNN-based models in computational efficiency. Recently, GPT and BERT demonstrate the efficacy of Transformer models on various NLP tasks using pre-trained language models on large-scale corpora.…

Computation and Language · Computer Science 2019-10-18 Chenguang Wang , Mu Li , Alexander J. Smola

How to effectively incorporate cross-utterance information cues into a neural language model (LM) has emerged as one of the intriguing issues for automatic speech recognition (ASR). Existing research efforts on improving contextualization…

Computation and Language · Computer Science 2021-10-04 Shih-Hsuan Chiu , Tien-Hong Lo , Fu-An Chao , Berlin Chen

Pretrained contextualized language models such as BERT have achieved impressive results on various natural language processing benchmarks. Benefiting from multiple pretraining tasks and large scale training corpora, pretrained models can…

Information Retrieval · Computer Science 2020-05-28 Zhiyu Chen , Mohamed Trabelsi , Jeff Heflin , Yinan Xu , Brian D. Davison