English
Related papers

Related papers: Modular Approach to Machine Reading Comprehension:…

200 papers

In open-ended continuous environments, robots need to learn multiple parameterised control tasks in hierarchical reinforcement learning. We hypothesise that the most complex tasks can be learned more easily by transferring knowledge from…

Artificial Intelligence · Computer Science 2021-02-22 Nicolas Duminy , Sao Mai Nguyen , Junshuai Zhu , Dominique Duhaut , Jerome Kerdreux

A crucial challenge in reinforcement learning is to reduce the number of interactions with the environment that an agent requires to master a given task. Transfer learning proposes to address this issue by re-using knowledge from previously…

Machine Learning · Computer Science 2023-04-28 Remo Sasso , Matthia Sabatelli , Marco A. Wiering

While pretrained models such as BERT have shown large gains across natural language understanding tasks, their performance can be improved by further training the model on a data-rich intermediate task, before fine-tuning it on a target…

A common way of learning to perform a task is to observe how it is carried out by experts. However, it is well known that for most tasks there is no unique way to perform them. This is especially noticeable the more complex the task is…

Artificial Intelligence · Computer Science 2024-04-04 David Nieves , María José Ramírez-Quintana , Carlos Monserrat , César Ferri , José Hernández-Orallo

Most uses of machine learning today involve training a model from scratch for a particular task, or sometimes starting with a model pretrained on a related task and then fine-tuning on a downstream task. Both approaches offer limited…

Machine Learning · Computer Science 2022-05-26 Andrea Gesmundo , Jeff Dean

Machine reading comprehension aims to teach machines to understand a text like a human and is a new challenging direction in Artificial Intelligence. This article summarizes recent advances in MRC, mainly focusing on two aspects (i.e.,…

Computation and Language · Computer Science 2019-07-04 Xin Zhang , An Yang , Sujian Li , Yizhong Wang

By routing input tokens to only a few split experts, Sparse Mixture-of-Experts has enabled efficient training of large language models. Recent findings suggest that fixing the routers can achieve competitive performance by alleviating the…

To efficiently select optimal dataset combinations for enhancing multi-task learning (MTL) performance in large language models, we proposed a novel framework that leverages a neural network to predict the best dataset combinations. The…

Computation and Language · Computer Science 2025-05-06 Zaifu Zhan , Rui Zhang

Mixtures of Experts (MoEs) have gained prominence in (self-)supervised learning due to their enhanced inference efficiency, adaptability to distributed training, and modularity. Previous research has illustrated that MoEs can significantly…

Machine Learning · Computer Science 2024-06-27 Timon Willi , Johan Obando-Ceron , Jakob Foerster , Karolina Dziugaite , Pablo Samuel Castro

Neurons in large language models often exhibit \emph{polysemanticity}, simultaneously encoding multiple unrelated concepts and obscuring interpretability. Instead of relying on post-hoc methods, we present \textbf{MoE-X}, a…

Statistical analysis of network data has attracted considerable attention in recent years, due to the rapid advancement of well-trained network models and the accessibility of large public network datasets. In this article, we propose a…

Methodology · Statistics 2026-04-22 Yong He , Kangxiang Qin , Haoran Tang

Existing research on continual learning of a sequence of tasks focused on dealing with catastrophic forgetting, where the tasks are assumed to be dissimilar and have little shared knowledge. Some work has also been done to transfer…

Machine Learning · Computer Science 2021-12-21 Zixuan Ke , Bing Liu , Xingchang Huang

An increasing number of well-trained deep networks have been released online by researchers and developers, enabling the community to reuse them in a plug-and-play way without accessing the training annotations. However, due to the large…

Machine Learning · Computer Science 2019-06-26 Sihui Luo , Xinchao Wang , Gongfan Fang , Yao Hu , Dapeng Tao , Mingli Song

Vision Transformers have emerged as the state-of-the-art models in various Computer Vision tasks, but their high computational and resource demands pose significant challenges. While Mixture-of-Experts (MoE) can make these models more…

Computer Vision and Pattern Recognition · Computer Science 2025-05-22 Uranik Berisha , Jens Mehnert , Alexandru Paul Condurache

Although existing machine reading comprehension models are making rapid progress on many datasets, they are far from robust. In this paper, we propose an understanding-oriented machine reading comprehension model to address three kinds of…

Computation and Language · Computer Science 2022-07-04 Feiliang Ren , Yongkang Liu , Bochao Li , Shilei Liu , Bingchao Wang , Jiaqi Wang , Chunchao Liu , Qi Ma

Neural networks have demonstrated significant advancements in Neural Machine Translation (NMT) compared to conventional phrase-based approaches. However, Multilingual Neural Machine Translation (MNMT) in extremely low-resource settings…

Computation and Language · Computer Science 2024-12-19 Vageesh Saxena , Sharid Loáiciga , Nils Rethmeier

In this paper, we address referring expression comprehension: localizing an image region described by a natural language expression. While most recent work treats expressions as a single unit, we propose to decompose them into three modular…

Computer Vision and Pattern Recognition · Computer Science 2018-03-28 Licheng Yu , Zhe Lin , Xiaohui Shen , Jimei Yang , Xin Lu , Mohit Bansal , Tamara L. Berg

In this paper, we present our first attempts in building a multilingual Neural Machine Translation framework under a unified approach. We are then able to employ attention-based NMT for many-to-many multilingual translation tasks. Our…

Computation and Language · Computer Science 2016-11-16 Thanh-Le Ha , Jan Niehues , Alexander Waibel

This paper presents a novel method that allows a machine learning algorithm following the transformation-based learning paradigm \cite{brill95:tagging} to be applied to multiple classification tasks by training jointly and simultaneously on…

Computation and Language · Computer Science 2007-05-23 Radu Florian , Grace Ngai

Training large-scale question answering systems is complicated because training sources usually cover a small portion of the range of possible questions. This paper studies the impact of multitask and transfer learning for simple question…

Machine Learning · Computer Science 2015-06-09 Antoine Bordes , Nicolas Usunier , Sumit Chopra , Jason Weston