Related papers: Multi-Layer Ensembling Techniques for Multilingual…

Ensembling BERT models often significantly improves accuracy, but at the cost of significantly more computation and memory footprint. In this work, we propose Multi-CLS BERT, a novel ensembling method for CLS-based prediction tasks that is…

Ensembling has a long history in statistical data analysis, with many impactful applications. However, in many modern machine learning settings, the benefits of ensembling are less ubiquitous and less obvious. We study, both theoretically…

Finetuning is a common practice widespread across different communities to adapt pretrained models to particular tasks. Text classification is one of these tasks for which many pretrained models are available. On the other hand, ensembles…

Ensembling is a powerful technique for improving the accuracy of machine learning models, with methods like stacking achieving strong results in tabular tasks. In time series forecasting, however, ensemble methods remain underutilized, with…

Despite the significant improvements achieved by large language models (LLMs) in English reasoning tasks, these models continue to struggle with multilingual reasoning. Recent studies leverage a full-parameter and two-stage training…

We propose a novel Transformer encoder-based architecture with syntactical knowledge encoded for intent detection and slot filling. Specifically, we encode syntactic knowledge into the Transformer encoder by jointly training it to predict…

Intent classification is a task in spoken language understanding. An intent classification system is usually implemented as a pipeline process, with a speech recognition module followed by text processing that classifies the intents. There…

Cross-lingual Summarization (CLS) aims at producing a summary in the target language for an article in the source language. Traditional solutions employ a two-step approach, i.e. translate then summarize or summarize then translate.…

Our work aimed at experimentally assessing the benefits of model ensembling within the context of neural methods for passage reranking. Starting from relatively standard neural models, we use a previous technique named Fast Geometric…

Ensembling has proven to be a powerful technique for boosting model performance, uncertainty estimation, and robustness in supervised learning. Advances in self-supervised learning (SSL) enable leveraging large unlabeled corpora for…

Massively multilingual sentence representation models, e.g., LASER, SBERT-distill, and LaBSE, help significantly improve cross-lingual downstream tasks. However, the use of a large amount of data or inefficient model architectures results…

Practical sequence classification tasks in natural language processing often suffer from low training data availability for target classes. Recent works towards mitigating this problem have focused on transfer learning using embeddings…

Ensembling is a successful technique to improve the performance of machine learning (ML) models. Conf-Ensemble is an adaptation to Boosting to create ensembles based on model confidence instead of model errors to better classify difficult…

End-to-end speech-to-intent classification has shown its advantage in harvesting information from both text and speech. In this paper, we study a technique to develop such an end-to-end system that supports multiple languages. To overcome…

Model ensembling is a well-established technique for improving the performance of machine learning models. Conventionally, this involves averaging the output distributions of multiple models and selecting the most probable label. This idea…

We propose a novel discriminative model that learns embeddings from multilingual and multi-modal data, meaning that our model can take advantage of images and descriptions in multiple languages to improve embedding quality. To that end, we…

In recent years, multi-label classification problem has become a controversial issue. In this kind of classification, each sample is associated with a set of class labels. Ensemble approaches are supervised learning algorithms in which an…

Emotion and intent recognition from speech is essential and has been widely investigated in human-computer interaction. The rapid development of social media platforms, chatbots, and other technologies has led to a large volume of speech…

Large Language Models (LLMs) have demonstrated impressive capabilities in language generation and general task performance. However, their application to spoken language understanding (SLU) remains challenging, particularly for token-level…

In recent times, with the exception of sporadic cases, the trend in Computer Vision is to achieve minor improvements compared to considerable increases in complexity. To reverse this trend, we propose a novel method to boost image…