Related papers: kNN-BOX: A Unified Framework for Nearest Neighbor …
The performance of Neural Network (NN)-based language models is steadily improving due to the emergence of new architectures, which are able to learn different natural language characteristics. This paper presents a novel framework, which…
Many works proposed methods to improve the performance of Neural Machine Translation (NMT) models in a domain/multi-domain adaptation scenario. However, an understanding of how NMT baselines represent text domain information internally is…
adaptNMT streamlines all processes involved in the development and deployment of RNN and Transformer neural translation models. As an open-source application, it is designed for both technical and non-technical users who work in the field…
Augmenting a language model (LM) with $k$-nearest neighbors ($k$NN) retrieval on its training data alone can decrease its perplexity, though the underlying reasons for this remain elusive. In this work, we rule out one previously posited…
kNN-MT presents a new paradigm for domain adaptation by building an external datastore, which usually saves all target language token occurrences in the parallel corpus. As a result, the constructed datastore is usually large and possibly…
The k-nearest neighbors (k-NN) classification rule has proven extremely successful in countless many computer vision applications. For example, image categorization often relies on uniform voting among the nearest prototypes in the space of…
Personalized models have demonstrated remarkable success in understanding and generating concepts provided by users. However, existing methods use separate concept tokens for understanding and generation, treating these tasks in isolation.…
Recent text-to-image models have achieved impressive results. However, since they require large-scale datasets of text-image pairs, it is impractical to train them on new domains where data is scarce or not labeled. In this work, we propose…
Merge trees are a valuable tool in the scientific visualization of scalar fields; however, current methods for merge tree comparisons are computationally expensive, primarily due to the exhaustive matching between tree nodes. To address…
Most dynamic ensemble selection (DES) methods utilize the K-Nearest Neighbors (KNN) algorithm to estimate the competence of classifiers in a small region surrounding the query sample. However, KNN is very sensitive to the local distribution…
Machine learning qualifies computers to assimilate with data, without being solely programmed [1, 2]. Machine learning can be classified as supervised and unsupervised learning. In supervised learning, computers learn an objective that…
Neural Machine Translation (NMT) models generally perform translation using a fixed-size lexical vocabulary, which is an important bottleneck on their generalization capability and overall translation quality. The standard approach to…
We propose a new neural network framework, termed Neural Network Machine Regression (NNMR), which integrates trainable input gating and adaptive depth regularization to jointly perform feature selection and function estimation in an…
Retrieval-augmented Neural Machine Translation models have been successful in many translation scenarios. Different from previous works that make use of mutually similar but redundant translation memories~(TMs), we propose a new…
While Transformer-based neural machine translation (NMT) is very effective in high-resource settings, many languages lack the necessary large parallel corpora to benefit from it. In the context of low-resource (LR) MT between two…
Existing 3D human motion generation and understanding methods often exhibit limited interpretability, restricting effective mutual enhancement between these inherently related tasks. While current unified frameworks based on large language…
In artificial intelligence (AI), knowledge is the information required by an intelligent system to accomplish tasks. While traditional knowledge bases use discrete, symbolic representations, detecting knowledge encoded in the continuous…
Machine Learning (ML) applications on healthcare can have a great impact on people's lives helping deliver better and timely treatment to those in need. At the same time, medical data is usually big and sparse requiring important…
Neural network techniques are widely applied to obtain high-quality distributed representations of words, i.e., word embeddings, to address text mining, information retrieval, and natural language processing tasks. Recently, efficient…
Template matching is a fundamental problem in computer vision with applications in fields including object detection, image registration, and object tracking. Current methods rely on nearest-neighbour (NN) matching, where the query feature…