Related papers: Data balancing for boosting performance of low-fre…

Self-supervised representation learning (SSRL) has demonstrated superior performance than supervised models for tasks including phoneme recognition. Training SSRL models poses a challenge for low-resource languages where sufficient…

Interest in dialog systems has grown substantially in the past decade. By extension, so too has interest in developing and improving intent classification and slot-filling models, which are two components that are commonly used in…

Class imbalance problems frequently occur in real-world tasks, and conventional deep learning algorithms are well known for performance degradation on imbalanced training datasets. To mitigate this problem, many approaches have aimed to…

Adapting vision-language models (VLMs) to downstream tasks with pseudolabels has gained increasing attention. A major obstacle is that the pseudolabels generated by VLMs tend to be imbalanced, leading to inferior performance. While existing…

Recent joint intent detection and slot tagging models have seen improved performance when compared to individual models. In many real-world datasets, the slot labels and values have a strong correlation with their intent labels. In such…

This study aims to explore the performance improvement method of large language models based on GPT-4 under the multi-task learning framework and conducts experiments on two tasks: text classification and automatic summary generation.…

We study the design decisions of publicly available instruction tuning methods, and break down the development of Flan 2022 (Chung et al., 2022). Through careful ablation studies on the Flan Collection of tasks and methods, we tease apart…

Multi-task learning (MTL) is a subfield of machine learning with important applications, but the multi-objective nature of optimization in MTL leads to difficulties in balancing training between tasks. The best MTL optimization methods…

Training and fine-tuning deep learning models, especially large language models (LLMs), on limited and imbalanced datasets poses substantial challenges. These issues often result in poor generalization, where models overfit to dominant…

Imbalanced learning (IL), i.e., learning unbiased models from class-imbalanced data, is a challenging problem. Typical IL methods including resampling and reweighting were designed based on some heuristic assumptions. They often suffer from…

In speech recognition problems, data scarcity often poses an issue due to the willingness of humans to provide large amounts of data for learning and classification. In this work, we take a set of 5 spoken Harvard sentences from 7 subjects…

Semantic frame parsing is a crucial component in spoken language understanding (SLU) to build spoken dialog systems. It has two main tasks: intent detection and slot filling. Although state-of-the-art approaches showed good results, they…

Multilinguality is crucial for extending recent advancements in language modelling to diverse linguistic communities. To maintain high performance while representing multiple languages, multilingual models ideally align representations,…

Large Language Model (LLM) workloads have distinct prefill and decode phases with different compute and memory requirements which should ideally be accounted for when scheduling input queries across different LLM instances in a cluster.…

We investigate automatic interlinear glossing in low-resource settings. We augment a hard-attentional neural model with embedded translation information extracted from interlinear glossed text. After encoding these translations using large…

Automated Speaking Assessment (ASA) plays a crucial role in evaluating second-language (L2) learners proficiency. However, ASA models often suffer from class imbalance, leading to biased predictions. To address this, we introduce a novel…

Practical needs of developing task-oriented dialogue assistants require the ability to understand many languages. Novel benchmarks for multilingual natural language understanding (NLU) include monolingual sentences in several languages,…

End-to-end spoken language understanding (SLU) models are a class of model architectures that predict semantics directly from speech. Because of their input and output types, we refer to them as speech-to-interpretation (STI) models.…

The rapid growth of voice assistants powered by large language models (LLM) has highlighted a need for speech instruction data to train these systems. Despite the abundance of speech recognition data, there is a notable scarcity of speech…

When the available data of a target speaker is insufficient to train a high quality speaker-dependent neural text-to-speech (TTS) system, we can combine data from multiple speakers and train a multi-speaker TTS model instead. Many studies…