Related papers: Multilingual Multi-modal Embeddings for Natural La…

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…

Using pre-trained word embeddings as input layer is a common practice in many natural language processing (NLP) tasks, but it is largely neglected for neural machine translation (NMT). In this paper, we conducted a systematic analysis on…

Neural approaches to learning term embeddings have led to improved computation of similarity and ranking in information retrieval (IR). So far neural representation learning has not been extended to meta-textual information that is readily…

The performance of Neural Machine Translation (NMT) systems often suffers in low-resource scenarios where sufficiently large-scale parallel corpora cannot be obtained. Pre-trained word embeddings have proven to be invaluable for improving…

In recent years, pretrained word embeddings have proved useful for multimodal neural machine translation (NMT) models to address the shortage of available datasets. However, the integration of pretrained word embeddings has not yet been…

This paper presents M3L-Contrast -- a novel multimodal multilingual (M3L) neural topic model for comparable data that maps texts from multiple languages and images into a shared topic space. Our model is trained jointly on texts and images…

To improve the performance of Neural Machine Translation~(NMT) for low-resource languages~(LRL), one effective strategy is to leverage parallel data from a related high-resource language~(HRL). However, multilingual data has been found more…

With an increase of dataset availability, the potential for learning from a variety of data sources has increased. One particular method to improve learning from multiple data sources is to embed the data source during training. This allows…

We present a novel technique for learning semantic representations, which extends the distributional hypothesis to multilingual data and joint-space embeddings. Our models leverage parallel data and learn to strongly align the embeddings of…

Word embeddings such as ELMo have recently been shown to model word semantics with greater efficacy through contextualized learning on large-scale language corpora, resulting in significant improvement in state of the art across many…

Natural language processing (NLP) tasks tend to suffer from a paucity of suitably annotated training data, hence the recent success of transfer learning across a wide variety of them. The typical recipe involves: (i) training a deep,…

Although all-in-one-model multilingual neural machine translation (multilingual NMT) has achieved remarkable progress, the convergence inconsistency in the joint training is ignored, i.e., different language pairs reaching convergence in…

Semantic embeddings have advanced the state of the art for countless natural language processing tasks, and various extensions to multimodal domains, such as visual-semantic embeddings, have been proposed. While the power of visual-semantic…

We introduce a novel suite of state-of-the-art bilingual text embedding models that are designed to support English and another target language. These models are capable of processing lengthy text inputs with up to 8192 tokens, making them…

With the aim of promoting and understanding the multilingual version of image search, we leverage visual object detection and propose a model with diverse multi-head attention to learn grounded multilingual multimodal representations.…

Matching images and sentences demands a fine understanding of both modalities. In this paper, we propose a new system to discriminatively embed the image and text to a shared visual-textual space. In this field, most existing works apply…

End-to-end neural machine translation has overtaken statistical machine translation in terms of translation quality for some language pairs, specially those with large amounts of parallel data. Besides this palpable improvement, neural…

In the current literature, most embedding models are based on the encoder-only transformer architecture to extract a dense and meaningful representation of the given input, which can be a text, an image, and more. With the recent advances…

Numerous embedding models have been recently explored to incorporate semantic knowledge into visual recognition. Existing methods typically focus on minimizing the distance between the corresponding images and texts in the embedding space…

Learning word embeddings using distributional information is a task that has been studied by many researchers, and a lot of studies are reported in the literature. On the contrary, less studies were done for the case of multiple languages.…