Related papers: Multi-Layer Ensembling Techniques for Multilingual…

Ensembling Large Language Models (LLMs) has gained attention as a promising approach to surpass the performance of individual models by leveraging their complementary strengths. In particular, aggregating models' next-token probability…

Despite the fact that data imbalance is becoming more and more common in real-world Spoken Language Understanding (SLU) applications, it has not been studied extensively in the literature. To the best of our knowledge, this paper presents…

Large language models (LLMs) have revolutionized various domains but still struggle with non-Latin scripts and low-resource languages. This paper addresses the critical challenge of improving multilingual performance without extensive…

Machine Reading Comprehension (MRC) is an active field in natural language processing with many successful developed models in recent years. Despite their high in-distribution accuracy, these models suffer from two issues: high training…

Multilingual Machine Translation promises to improve translation quality between non-English languages. This is advantageous for several reasons, namely lower latency (no need to translate twice), and reduced error cascades (e.g., avoiding…

Feature-importance methods show promise in transforming machine learning models from predictive engines into tools for scientific discovery. However, due to data sampling and algorithmic stochasticity, expressive models can be unstable,…

Natural language understanding (NLU) has two core tasks: intent classification and slot filling. The success of pre-training language models resulted in a significant breakthrough in the two tasks. One of the promising solutions called BERT…

Despite the progress of image segmentation for accurate visual entity segmentation, completing the diverse requirements of image editing applications for different-level region-of-interest selections remains unsolved. In this paper, we…

Identifying intents from dialogue utterances forms an integral component of task-oriented dialogue systems. Intent-related tasks are typically formulated either as a classification task, where the utterances are classified into predefined…

Ensemble approaches for deep-learning-based semantic segmentation remain insufficiently explored despite the proliferation of competitive benchmarks and downstream applications. In this work, we explore and benchmark the popular ensembling…

Intent classification is a fundamental task in the spoken language understanding field that has recently gained the attention of the scientific community, mainly because of the feasibility of approaching it with end-to-end neural models. In…

Slot-filling and intent detection are well-established tasks in Conversational AI. However, current large-scale benchmarks for these tasks often exclude evaluations of low-resource languages and rely on translations from English benchmarks,…

Novel and high-performance medical image classification pipelines are heavily utilizing ensemble learning strategies. The idea of ensemble learning is to assemble diverse models or multiple predictions and, thus, boost prediction…

Model ensembling is a technique to combine the predicted distributions of two or more models, often leading to improved robustness and performance. For ensembling in text generation, the next token's probability distribution is derived from…

Intermediate task transfer learning can greatly improve model performance. If, for example, one has little training data for emotion detection, first fine-tuning a language model on a sentiment classification dataset may improve performance…

Ensembling a neural network is a widely recognized approach to enhance model performance, estimate uncertainty, and improve robustness in deep supervised learning. However, deep ensembles often come with high computational costs and memory…

This study introduces an ensemble framework for unstructured text categorization using large language models (LLMs). By integrating multiple models, the ensemble large language model (eLLM) framework addresses common weaknesses of…

Speech emotion recognition has evolved from research to practical applications. Previous studies of emotion recognition from speech have focused on developing models on certain datasets like IEMOCAP. The lack of data in the domain of…

As global demand for multilingual large language models (LLMs) grows, most LLMs still remain overly focused on English, leading to the limited access to advanced AI for non-English speakers. Current methods to enhance multilingual…

In this paper, we introduce the use of Semantic Hashing as embedding for the task of Intent Classification and achieve state-of-the-art performance on three frequently used benchmarks. Intent Classification on a small dataset is a…