Related papers: Learning Decoupled Retrieval Representation for Ne…
Compared to sentence-level systems, document-level neural machine translation (NMT) models produce a more consistent output across a document and are able to better resolve ambiguities within the input. There are many works on…
One of the significant challenges of Machine Translation (MT) is the scarcity of large amounts of data, mainly parallel sentence aligned corpora. If the evaluation is as rigorous as resource-rich languages, both Neural Machine Translation…
In this work we formulate the problem of image captioning as a multimodal translation task. Analogous to machine translation, we present a sequence-to-sequence recurrent neural networks (RNN) model for image caption generation. Different…
How to effectively adapt neural machine translation (NMT) models according to emerging cases without retraining? Despite the great success of neural machine translation, updating the deployed models online remains a challenge. Existing…
Traditional neural machine translation is limited to the topmost encoder layer's context representation and cannot directly perceive the lower encoder layers. Existing solutions usually rely on the adjustment of network architecture, making…
While neural machine translation (NMT) models provide improved translation quality in an elegant, end-to-end framework, it is less clear what they learn about language. Recent work has started evaluating the quality of vector…
Word alignment has proven to benefit many-to-many neural machine translation (NMT). However, high-quality ground-truth bilingual dictionaries were used for pre-editing in previous methods, which are unavailable for most language pairs.…
Although end-to-end Neural Machine Translation (NMT) has achieved remarkable progress in the past two years, it suffers from a major drawback: translations generated by NMT systems often lack of adequacy. It has been widely observed that…
The current models of image representation based on Convolutional Neural Networks (CNN) have shown tremendous performance in image retrieval. Such models are inspired by the information flow along the visual pathway in the human visual…
In the field of machine learning, the well-trained model is assumed to be able to recover the training labels, i.e. the synthetic labels predicted by the model should be as close to the ground-truth labels as possible. Inspired by this, we…
As important data carriers, the drastically increasing number of multimedia videos often brings many duplicate and near-duplicate videos in the top results of search. Near-duplicate video retrieval (NDVR) can cluster and filter out the…
Retrieval-augmented language models (LMs) have received much attention recently. However, typically the retriever is not trained jointly as a native component of the LM, but added post-hoc to an already-pretrained LM, which limits the…
Self-supervised neural machine translation (SSNMT) jointly learns to identify and select suitable training data from comparable (rather than parallel) corpora and to translate, in a way that the two tasks support each other in a virtuous…
Unsupervised image retrieval aims to learn the important visual characteristics without any given level to retrieve the similar images for a given query image. The Convolutional Neural Network (CNN)-based approaches have been extensively…
Monolingual data has been demonstrated to be helpful in improving the translation quality of neural machine translation (NMT). The current methods stay at the usage of word-level knowledge, such as generating synthetic parallel data or…
Large language models (LLMs) often hallucinate and lack the ability to provide attribution for their generations. Semi-parametric LMs, such as kNN-LM, approach these limitations by refining the output of an LM for a given prompt using its…
Nearest neighbor (NN) sampling provides more semantic variations than pre-defined transformations for self-supervised learning (SSL) based image recognition problems. However, its performance is restricted by the quality of the support set,…
Speech recognition performance varies by language, domain, and speaker characteristics such as accent, but fine-tuning a model on any of these categories may lead to catastrophic forgetting. Token-level $k$ nearest neighbor search ($k$NN),…
Document-level machine translation incorporates inter-sentential dependencies into the translation of a source sentence. In this paper, we propose a new framework to model cross-sentence dependencies by training neural machine translation…
Despite the growing variety of languages supported by existing multilingual neural machine translation (MNMT) models, most of the world's languages are still being left behind. We aim to extend large-scale MNMT models to incorporate a new…