English
Related papers

Related papers: Improving Neural Language Models with a Continuous…

200 papers

Large Language Models (LLMs) have become a mainstay for many everyday applications. However, as data evolve their knowledge quickly becomes outdated. Continual learning aims to update LLMs with new information without erasing previously…

Machine Learning · Computer Science 2026-01-05 Thomas Katraouras , Dimitrios Rafailidis

With the rapid development of large language models, AI assistants like ChatGPT have become increasingly integrated into people's works and lives but are limited in personalized services. In this paper, we present a plug-and-play framework…

Computation and Language · Computer Science 2024-10-15 Ruifeng Yuan , Shichao Sun , Yongqi Li , Zili Wang , Ziqiang Cao , Wenjie Li

Memory retention challenges in deep neural architectures have ongoing limitations in the ability to process and recall extended contextual information. Token dependencies degrade as sequence length increases, leading to a decline in…

Computation and Language · Computer Science 2025-03-26 Frederick Dillon , Gregor Halvorsen , Simon Tattershall , Magnus Rowntree , Gareth Vanderpool

Recently, there has been interest in multiplicative recurrent neural networks for language modeling. Indeed, simple Recurrent Neural Networks (RNNs) encounter difficulties recovering from past mistakes when generating sequences due to high…

Machine Learning · Computer Science 2019-07-02 Diego Maupomé , Marie-Jean Meurs

Continual learning of deep neural networks is a key requirement for scaling them up to more complex applicative scenarios and for achieving real lifelong learning of these architectures. Previous approaches to the problem have considered…

Machine Learning · Computer Science 2020-06-25 Jary Pomponi , Simone Scardapane , Vincenzo Lomonaco , Aurelio Uncini

Despite the remarkable progress recently made in distant speech recognition, state-of-the-art technology still suffers from a lack of robustness, especially when adverse acoustic conditions characterized by non-stationary noises and…

Computation and Language · Computer Science 2017-03-24 Mirco Ravanelli , Philemon Brakel , Maurizio Omologo , Yoshua Bengio

We propose an end-to-end model based on convolutional and recurrent neural networks for speech enhancement. Our model is purely data-driven and does not make any assumptions about the type or the stationarity of the noise. In contrast to…

Sound · Computer Science 2018-05-03 Han Zhao , Shuayb Zarar , Ivan Tashev , Chin-Hui Lee

Modern language models predict the next token in the sequence by considering the past text through a powerful function such as attention. However, language models have no explicit mechanism that allows them to spend computation time for…

Computation and Language · Computer Science 2024-09-04 Florian Mai , Nathan Cornille , Marie-Francine Moens

Neural machine translation (NMT) has achieved notable success in recent times, however it is also widely recognized that this approach has limitations with handling infrequent words and word pairs. This paper presents a novel…

Computation and Language · Computer Science 2017-08-08 Yang Feng , Shiyue Zhang , Andi Zhang , Dong Wang , Andrew Abel

Recent Active Learning (AL) approaches in Natural Language Processing (NLP) proposed using off-the-shelf pretrained language models (LMs). In this paper, we argue that these LMs are not adapted effectively to the downstream task during AL…

Computation and Language · Computer Science 2022-03-03 Katerina Margatina , Loïc Barrault , Nikolaos Aletras

Transformer-based language models (LMs) track contextual information through large, hard-coded input windows. We introduce MemoryPrompt, a leaner approach in which the LM is complemented by a small auxiliary recurrent network that passes…

Computation and Language · Computer Science 2024-02-26 Nathanaël Carraz Rakotonirina , Marco Baroni

Deep neural networks have achieved state-of-the-art results in various vision and/or language tasks. Despite the use of large training datasets, most models are trained by iterating over single input-output pairs, discarding the remaining…

Computation and Language · Computer Science 2021-04-27 Rita Parada Ramos , Patrícia Pereira , Helena Moniz , Joao Paulo Carvalho , Bruno Martins

Users of Augmentative and Alternative Communication (AAC) may write letter-by-letter via an interface that uses a character language model. However, most state-of-the-art large pretrained language models predict subword tokens of variable…

Computation and Language · Computer Science 2025-10-03 Dylan Gaines , Keith Vertanen

With the rapid development and widespread use of advanced network systems, software vulnerabilities pose a significant threat to secure communications and networking. Learning-based vulnerability detection systems, particularly those…

Cryptography and Security · Computer Science 2024-10-04 Weiliang Qi , Jiahao Cao , Darsh Poddar , Sophia Li , Xinda Wang

Today, the dominant paradigm for training neural networks involves minimizing task loss on a large dataset. Using world knowledge to inform a model, and yet retain the ability to perform end-to-end training remains an open question. In this…

Machine Learning · Computer Science 2020-08-21 Tao Li , Vivek Srikumar

Inducing sparseness while training neural networks has been shown to yield models with a lower memory footprint but similar effectiveness to dense models. However, sparseness is typically induced starting from a dense model, and thus this…

Machine Learning · Computer Science 2022-03-30 Thomas Demeester , Johannes Deleu , Fréderic Godin , Chris Develder

Large language models are strong sequence predictors, yet standard inference relies on immutable context histories. After making an error at generation step t, the model lacks an updatable memory mechanism that improves predictions for step…

Computation and Language · Computer Science 2026-01-21 Yuxing Lu , J. Ben Tamo , Weichen Zhao , Nan Sun , Yishan Zhong , Wenqi Shi , Jinzhuo Wang , May D. Wang

We present a novel class incremental learning approach based on deep neural networks, which continually learns new tasks with limited memory for storing examples in the previous tasks. Our algorithm is based on knowledge distillation and…

Machine Learning · Computer Science 2022-04-05 Minsoo Kang , Jaeyoo Park , Bohyung Han

We investigate the use of extended context in attention-based neural machine translation. We base our experiments on translated movie subtitles and discuss the effect of increasing the segments beyond single translation units. We study the…

Computation and Language · Computer Science 2017-08-22 Jörg Tiedemann , Yves Scherrer

We propose a method of stacking multiple long short-term memory (LSTM) layers for modeling sentences. In contrast to the conventional stacked LSTMs where only hidden states are fed as input to the next layer, the suggested architecture…

Computation and Language · Computer Science 2019-11-04 Jihun Choi , Taeuk Kim , Sang-goo Lee