Related papers: Cross Language Text Classification via Subspace Co…

We consider zero-shot cross-lingual transfer in legal topic classification using the recent MultiEURLEX dataset. Since the original dataset contains parallel documents, which is unrealistic for zero-shot cross-lingual transfer, we develop a…

We tackle the task of automatically discriminating between human and machine translations. As opposed to most previous work, we perform experiments in a multilingual setting, considering multiple languages and multilingual pretrained…

Multi-task learning in text classification leverages implicit correlations among related tasks to extract common features and yield performance gains. However, most previous works treat labels of each task as independent and meaningless…

We review motivations, definition, approaches, and methodology for unsupervised cross-lingual learning and call for a more rigorous position in each of them. An existing rationale for such research is based on the lack of parallel data for…

We introduce DocSCAN, a completely unsupervised text classification approach using Semantic Clustering by Adopting Nearest-Neighbors (SCAN). For each document, we obtain semantically informative vectors from a large pre-trained language…

Contrastive Language-Image Pre-training (CLIP) has been a celebrated method for training vision encoders to generate image/text representations facilitating various applications. Recently, CLIP has been widely adopted as the vision backbone…

Multi-view representation learning has developed rapidly over the past decades and has been applied in many fields. However, most previous works assumed that each view is complete and aligned. This leads to an inevitable deterioration in…

Sparse language vectors from linguistic typology databases and learned embeddings from tasks like multilingual machine translation have been investigated in isolation, without analysing how they could benefit from each other's language…

The natural world is abundant with concepts expressed via visual, acoustic, tactile, and linguistic modalities. Much of the existing progress in multimodal learning, however, focuses primarily on problems where the same set of modalities…

Machine learning-based multi-label medical text classifications can be used to enhance the understanding of the human body and aid the need for patient care. We present a broad study on clinical natural language processing techniques to…

Current approaches to learning vector representations of text that are compatible between different languages usually require some amount of parallel text, aligned at word, sentence or at least document level. We hypothesize however, that…

Until recently, the number of public real-world text images was insufficient for training scene text recognizers. Therefore, most modern training methods rely on synthetic data and operate in a fully supervised manner. Nevertheless, the…

Pre-trained language models have been shown to improve performance in many natural language tasks substantially. Although the early focus of such models was single language pre-training, recent advances have resulted in cross-lingual and…

With the rise of deep learning, large datasets and complex models have become common, requiring significant computing power. To address this, data distillation has emerged as a technique to quickly train models with lower memory and time…

Crosslingual word embeddings represent lexical items from different languages in the same vector space, enabling transfer of NLP tools. However, previous attempts had expensive resource requirements, difficulty incorporating monolingual…

We present a method for the classification of multi-labelled text documents explicitly designed for data stream applications that require to process a virtually infinite sequence of data using constant memory and constant processing time.…

Multi-domain text classification can automatically classify texts in various scenarios. Due to the diversity of human languages, texts with the same label in different domains may differ greatly, which brings challenges to the multi-domain…

Unsupervised learning of cross-lingual word embedding offers elegant matching of words across languages, but has fundamental limitations in translating sentences. In this paper, we propose simple yet effective methods to improve…

Cross-lingual word embeddings are becoming increasingly important in multilingual NLP. Recently, it has been shown that these embeddings can be effectively learned by aligning two disjoint monolingual vector spaces through linear…

In this work, we present an information-theoretic framework that formulates cross-lingual language model pre-training as maximizing mutual information between multilingual-multi-granularity texts. The unified view helps us to better…