English
Related papers

Related papers: Scheduled Sampling for Transformers

200 papers

Recent works using artificial neural networks based on word distributed representation greatly boost the performance of various natural language learning tasks, especially question answering. Though, they also carry along with some…

Computation and Language · Computer Science 2016-12-23 Lingxun Meng , Yan Li , Mengyi Liu , Peng Shu

We present an algorithm for controlling and scheduling multiple linear time-invariant processes on a shared bandwidth limited communication network using adaptive sampling intervals. The controller is centralized and computes at every…

Systems and Control · Computer Science 2015-06-25 Erik Henriksson , Daniel E. Quevedo , Edwin G. W. Peters , Henrik Sandberg , Karl Henrik Johansson

Predictive process monitoring is a subfield of process mining that aims to estimate case or event features for running process instances. Such predictions are of significant interest to the process stakeholders. However, most of the…

We study prediction of future outcomes with supervised models that use privileged information during learning. The privileged information comprises samples of time series observed between the baseline time of prediction and the future…

Position embeddings, encoding the positional relationships among tokens in text sequences, make great contributions to modeling local context features in Transformer-based pre-trained language models. However, in Extractive Question…

Computation and Language · Computer Science 2023-11-21 Mingxu Tao , Yansong Feng , Dongyan Zhao

Representation learning for text via pretraining a language model on a large corpus has become a standard starting point for building NLP systems. This approach stands in contrast to autoencoders, also trained on raw text, but with the…

Computation and Language · Computer Science 2021-09-14 Ivan Montero , Nikolaos Pappas , Noah A. Smith

Attention mechanism in sequence-to-sequence models is designed to model the alignments between acoustic features and output tokens in speech recognition. However, attention weights produced by models trained end to end do not always…

Audio and Speech Processing · Electrical Eng. & Systems 2022-04-27 Gene-Ping Yang , Hao Tang

Transformers underpin modern large language models (LLMs) and are commonly assumed to be behaviorally unstructured at random initialization, with all meaningful preferences emerging only through large-scale training. We challenge this…

Machine Learning · Statistics 2026-02-06 Siquan Li , Yao Tong , Haonan Wang , Tianyang Hu

Spatio-temporal sequence forecasting is one of the fundamental tasks in spatio-temporal data mining. It facilitates many real world applications such as precipitation nowcasting, citywide crowd flow prediction and air pollution forecasting.…

Machine Learning · Computer Science 2020-05-20 Hong-Bin Liu , Ickjai Lee

Temporal credit assignment in reinforcement learning is challenging due to delayed and stochastic outcomes. Monte Carlo targets can bridge long delays between action and consequence but lead to high-variance targets due to stochasticity.…

Machine Learning · Computer Science 2024-06-05 Aditya A. Ramesh , Kenny Young , Louis Kirsch , Jürgen Schmidhuber

As the application space of language models continues to evolve, a natural question to ask is how we can quickly adapt models to new tasks. We approach this classic question from a continual learning perspective, in which we aim to continue…

Computation and Language · Computer Science 2023-07-13 Adam Fisch , Amal Rannen-Triki , Razvan Pascanu , Jörg Bornschein , Angeliki Lazaridou , Elena Gribovskaya , Marc'Aurelio Ranzato

In this work we propose for the first time a transformer-based framework for unsupervised representation learning of multivariate time series. Pre-trained models can be potentially used for downstream tasks such as regression and…

Machine Learning · Computer Science 2020-12-10 George Zerveas , Srideepika Jayaraman , Dhaval Patel , Anuradha Bhamidipaty , Carsten Eickhoff

Continual pre-training has demonstrated significant potential in enhancing model performance, particularly in domain-specific scenarios. The most common approach for packing data before continual pre-training involves concatenating input…

Computation and Language · Computer Science 2025-05-30 Ruicheng Yin , Xuan Gao , Changze Lv , Xiaohua Wang , Xiaoqing Zheng , Xuanjing Huang

We are interested in how to design reinforcement learning agents that provably reduce the sample complexity for learning new tasks by transferring knowledge from previously-solved ones. The availability of solutions to related problems…

Machine Learning · Computer Science 2020-07-03 Andrea Tirinzoni , Riccardo Poiani , Marcello Restelli

In this paper, we propose Test-Time Training, a general approach for improving the performance of predictive models when training and test data come from different distributions. We turn a single unlabeled test sample into a self-supervised…

Machine Learning · Computer Science 2020-07-03 Yu Sun , Xiaolong Wang , Zhuang Liu , John Miller , Alexei A. Efros , Moritz Hardt

The Transformer model has revolutionized Natural Language Processing tasks such as Neural Machine Translation, and many efforts have been made to study the Transformer architecture, which increased its efficiency and accuracy. One potential…

Computation and Language · Computer Science 2023-08-17 Daniela N. Rim , Kimera Richard , Heeyoul Choi

In this paper, we propose three methods for generating synthetic samples to train and evaluate multimodal large language models capable of processing both text and speech inputs. Addressing the scarcity of samples containing both…

Audio and Speech Processing · Electrical Eng. & Systems 2024-06-21 Vahid Noroozi , Zhehuai Chen , Somshubra Majumdar , Steve Huang , Jagadeesh Balam , Boris Ginsburg

Real-world sequential signals, such as audio or video, contain critical information that is often embedded within long periods of silence or noise. While recurrent neural networks (RNNs) are designed to process such data efficiently, they…

Machine Learning · Computer Science 2026-05-01 Bojian Yin , Shurong Wang , Haoyu Tan , Sander Bohte , Federico Corradi , Guoqi Li

We present two approaches that use unlabeled data to improve sequence learning with recurrent networks. The first approach is to predict what comes next in a sequence, which is a conventional language model in natural language processing.…

Machine Learning · Computer Science 2015-11-05 Andrew M. Dai , Quoc V. Le

The dominant approach to sequence generation is to produce a sequence in some predefined order, e.g. left to right. In contrast, we propose a more general model that can generate the output sequence by inserting tokens in any arbitrary…

Computation and Language · Computer Science 2019-11-04 Dmitrii Emelianenko , Elena Voita , Pavel Serdyukov