English
Related papers

Related papers: Adaptive Input Representations for Neural Language…

200 papers

We propose several ways of reusing subword embeddings and other weights in subword-aware neural language models. The proposed techniques do not benefit a competitive character-aware model, but some of them improve the performance of…

Computation and Language · Computer Science 2018-04-26 Zhenisbek Assylbekov , Rustem Takhanov

The softmax attention mechanism has emerged as a noteworthy development in the field of Artificial Intelligence research, building on the successes of Transformer-based architectures. However, their ever increasing sizes necessitate ever…

Computation and Language · Computer Science 2023-05-19 Luca Herranz-Celotti , Ermal Rrapaj

In 2018, Mikolov et al. introduced the positional language model, which has characteristics of attention-based neural machine translation models and which achieved state-of-the-art performance on the intrinsic word analogy task. However,…

Computation and Language · Computer Science 2022-03-01 Vít Novotný , Michal Štefánik , Eniafe Festus Ayetiran , Petr Sojka , Radim Řehůřek

Neural machine translation (NMT) models are typically trained with fixed-size input and output vocabularies, which creates an important bottleneck on their accuracy and generalization capability. As a solution, various studies proposed…

Computation and Language · Computer Science 2018-05-08 Duygu Ataman , Marcello Federico

Neural machine translation has recently achieved impressive results, while using little in the way of external linguistic information. In this paper we show that the strong learning capability of neural MT models does not make linguistic…

Computation and Language · Computer Science 2016-06-29 Rico Sennrich , Barry Haddow

Recent advances in language modeling consist in pretraining highly parameterized neural networks on extremely large web-mined text corpora. Training and inference with such models can be costly in practice, which incentivizes the use of…

Computation and Language · Computer Science 2024-04-12 Nathan Godey , Éric de la Clergerie , Benoît Sagot

We present a family of neural-network--inspired models for computing continuous word representations, specifically designed to exploit both monolingual and multilingual text. This framework allows us to perform unsupervised training of…

Computation and Language · Computer Science 2016-12-15 Radu Soricut , Nan Ding

We explore why deep convolutional neural networks (CNNs) with small two-dimensional kernels, primarily used for modeling spatial relations in images, are also effective in speech recognition. We analyze the representations learned by deep…

Computation and Language · Computer Science 2018-11-13 Joanna Rownicka , Peter Bell , Steve Renals

While word embeddings are currently predominant for natural language processing, most of existing models learn them solely from their contexts. However, these context-based word embeddings are limited since not all words' meaning can be…

Computation and Language · Computer Science 2016-08-23 Jifan Chen , Kan Chen , Xipeng Qiu , Qi Zhang , Xuanjing Huang , Zheng Zhang

Dialogue act recognition is an important component of a large number of natural language processing pipelines. Many research works have been carried out in this area, but relatively few investigate deep neural networks and word embeddings.…

Computation and Language · Computer Science 2020-10-23 Christophe Cerisara , Pavel Kral , Ladislav Lenc

The current standard approach for fine-tuning transformer-based language models includes a fixed number of training epochs and a linear learning rate schedule. In order to obtain a near-optimal model for the given downstream task, a search…

Computation and Language · Computer Science 2022-02-08 Felix Stollenwerk

Transformer models typically calculate attention matrices using dot products, which have limitations when capturing nonlinear relationships between embedding vectors. We propose Neural Attention, a technique that replaces dot products with…

Machine Learning · Computer Science 2025-11-10 Andrew DiGiugno , Ausif Mahmood

In this study, we aim to explore efficient tuning methods for speech self-supervised learning. Recent studies show that self-supervised learning (SSL) can learn powerful representations for different speech tasks. However, fine-tuning…

Audio and Speech Processing · Electrical Eng. & Systems 2023-01-31 Zih-Ching Chen , Chin-Lun Fu , Chih-Ying Liu , Shang-Wen Li , Hung-yi Lee

The great success of transformer-based models in natural language processing (NLP) has led to various attempts at adapting these architectures to other domains such as vision and audio. Recent work has shown that transformers can outperform…

Sound · Computer Science 2023-01-26 Khaled Koutini , Jan Schlüter , Hamid Eghbal-zadeh , Gerhard Widmer

We evaluate machine comprehension models' robustness to noise and adversarial attacks by performing novel perturbations at the character, word, and sentence level. We experiment with different amounts of perturbations to examine model…

Computation and Language · Computer Science 2020-05-04 Winston Wu , Dustin Arendt , Svitlana Volkova

We study model pruning methods applied to Transformer-based neural network language models for automatic speech recognition. We explore three aspects of the pruning frame work, namely criterion, method and scheduler, analyzing their…

Machine Learning · Computer Science 2023-10-06 Leonardo Emili , Thiago Fraga-Silva , Ernest Pusateri , Markus Nußbaum-Thom , Youssef Oualil

Language models typically need to be trained or finetuned in order to acquire new knowledge, which involves updating their weights. We instead envision language models that can simply read and memorize new data at inference time, thus…

Machine Learning · Computer Science 2022-03-18 Yuhuai Wu , Markus N. Rabe , DeLesley Hutchins , Christian Szegedy

Transformer-based language models have recently been at the forefront of active research in text generation. However, these models' advances come at the price of prohibitive training costs, with parameter counts in the billions and compute…

Computation and Language · Computer Science 2025-02-04 Gabriel Lindenmaier , Sean Papay , Sebastian Padó

Natural Language Processing (NLP) systems commonly leverage bag-of-words co-occurrence techniques to capture semantic and syntactic word relationships. The resulting word-level distributed representations often ignore morphological…

Computation and Language · Computer Science 2015-06-12 Andrew Trask , David Gilmore , Matthew Russell

Increasing model size when pretraining natural language representations often results in improved performance on downstream tasks. However, at some point further model increases become harder due to GPU/TPU memory limitations and longer…

Computation and Language · Computer Science 2020-02-11 Zhenzhong Lan , Mingda Chen , Sebastian Goodman , Kevin Gimpel , Piyush Sharma , Radu Soricut