Related papers: Few-shot Learning for Multi-label Intent Detection
In text classification tasks, useful information is encoded in the label names. Label semantic aware systems have leveraged this information for improved text classification performance during fine-tuning and prediction. However, use of…
Recently deep learning has dominated many machine learning areas, including spoken language understanding (SLU). However, deep learning models are notorious for being data-hungry, and the heavily optimized models are usually sensitive to…
Instance-level image classification tasks have traditionally relied on single-instance labels to train models, e.g., few-shot learning and transfer learning. However, set-level coarse-grained labels that capture relationships among…
In this paper, we propose a novel deep learning architecture for multi-label zero-shot learning (ML-ZSL), which is able to predict multiple unseen class labels for each input instance. Inspired by the way humans utilize semantic knowledge…
Few-shot Learning (FSL) aims to classify new concepts from a small number of examples. While there have been an increasing amount of work on few-shot object classification in the last few years, most current approaches are limited to images…
Training a neural network model that can quickly adapt to a new task is highly desirable yet challenging for few-shot learning problems. Recent few-shot learning methods mostly concentrate on developing various meta-learning strategies from…
Distribution estimation has been demonstrated as one of the most effective approaches in dealing with few-shot image classification, as the low-level patterns and underlying representations can be easily transferred across different tasks…
We study few-shot learning in natural language domains. Compared to many existing works that apply either metric-based or optimization-based meta-learning to image domain with low inter-task variance, we consider a more realistic setting,…
In-context learning (ICL) using large language models for tasks with many labels is challenging due to the limited context window, which makes it difficult to fit a sufficient number of examples in the prompt. In this paper, we use a…
Continual learning strives to ensure stability in solving previously seen tasks while demonstrating plasticity in a novel domain. Recent advances in continual learning are mostly confined to a supervised learning setting, especially in NLP…
Multi-label classification is a type of supervised learning where an instance may belong to multiple labels simultaneously. Predicting each label independently has been criticized for not exploiting any correlation between labels. In this…
Few-shot learning-the ability to train models with access to limited data-has become increasingly popular in the natural language processing (NLP) domain, as large language models such as GPT and T0 have been empirically shown to achieve…
Few-shot classification tends to struggle when it needs to adapt to diverse domains. Due to the non-overlapping label space between domains, the performance of conventional domain adaptation is limited. Previous work tackles the problem in…
In the realm of digital music, using tags to efficiently organize and retrieve music from extensive databases is crucial for music catalog owners. Human tagging by experts is labor-intensive but mostly accurate, whereas automatic tagging…
Large Language Models (LLMs) have shown strong performance on NLP classification tasks. However, they typically rely on aggregated labels-often via majority voting-which can obscure the human disagreement inherent in subjective annotations.…
In task-oriented dialogue systems, intent detection is crucial for interpreting user queries and providing appropriate responses. Existing research primarily addresses simple queries with a single intent, lacking effective systems for…
Few-shot classification aims to learn to classify new object categories well using only a few labeled examples. Transferring feature representations from other models is a popular approach for solving few-shot classification problems. In…
The success of deep learning methods hinges on the availability of large training datasets annotated for the task of interest. In contrast to human intelligence, these methods lack versatility and struggle to learn and adapt quickly to new…
Intent detection is one of the core components of goal-oriented dialog systems, and detecting out-of-scope (OOS) intents is also a practically important skill. Few-shot learning is attracting much attention to mitigate data scarcity, but…
Currently, the state-of-the-art methods treat few-shot semantic segmentation task as a conditional foreground-background segmentation problem, assuming each class is independent. In this paper, we introduce the concept of meta-class, which…