Related papers: Rainbow Keywords: Efficient Incremental Learning f…

Recommender systems (RSs) play a pervasive role in today's online services, yet their closed-loop nature constrains their access to open-world knowledge. Recently, large language models (LLMs) have shown promise in bridging this gap.…

Keyword spotting (KWS) is an important technique for speech applications, which enables users to activate devices by speaking a keyword phrase. Although a phoneme classifier can be used for KWS, exploiting a large amount of transcribed data…

In this paper, we propose a novel Reinforcement Learning approach for solving the Active Information Acquisition problem, which requires an agent to choose a sequence of actions in order to acquire information about a process of interest…

Traditional object detectors are ill-equipped for incremental learning. However, fine-tuning directly on a well-trained detection model with only new data will lead to catastrophic forgetting. Knowledge distillation is a flexible way to…

Current unlearning methods for large language models usually rely on reverse optimization to reduce target token probabilities. However, this paradigm disrupts the subsequent tokens prediction, degrading model performance and linguistic…

Multi-class supervised learning systems require the knowledge of the entire range of labels they predict. Often when learnt incrementally, they suffer from catastrophic forgetting. To avoid this, generous leeways have to be made to the…

Keyword spotting (KWS) is one of the speech recognition tasks most sensitive to the quality of the feature representation. However, the research on KWS has traditionally focused on new model topologies, putting little emphasis on other…

A common challenge in continual learning (CL) is catastrophic forgetting, where the performance on old tasks drops after new, additional tasks are learned. In this paper, we propose a novel framework called ReCL to slow down forgetting in…

Currently used semantic parsing systems deployed in voice assistants can require weeks to train. Datasets for these models often receive small and frequent updates, data patches. Each patch requires training a new model. To reduce training…

Real-life multilingual systems should be able to efficiently incorporate new languages as data distributions fed to the system evolve and shift over time. To do this, systems need to handle the issue of catastrophic forgetting, where the…

Continual learning for Semantic Segmentation (CSS) is a rapidly emerging field, in which the capabilities of the segmentation model are incrementally improved by learning new classes or new domains. A central challenge in Continual Learning…

Event detection is one of the fundamental tasks in information extraction and knowledge graph. However, a realistic event detection system often needs to deal with new event classes constantly. These new classes usually have only a few…

Retrieval-augmented generation (RAG) is a powerful method for enhancing natural language generation by integrating external knowledge into a model's output. While prior work has demonstrated the importance of improving knowledge retrieval…

Few-shot keyword spotting (KWS) aims to detect unknown keywords with limited training samples. A commonly used approach is the pre-training and fine-tuning framework. While effective in clean conditions, this approach struggles with mixed…

A keyword spotting (KWS) system determines the existence of, usually predefined, keyword in a continuous speech stream. This paper presents a query-by-example on-device KWS system which is user-specific. The proposed system consists of two…

Self-supervised speech representation learning (S3RL) is revolutionizing the way we leverage the ever-growing availability of data. While S3RL related studies typically use large models, we employ light-weight networks to comply with tight…

Generating keyphrases that summarize the main points of a document is a fundamental task in natural language processing. Although existing generative models are capable of predicting multiple keyphrases for an input document as well as…

Open-vocabulary keyword spotting (KWS) refers to the task of detecting words or terms within speech recordings, regardless of whether they were included in the training data. This paper introduces an open-vocabulary keyword spotting model…

Reinforcement learning (RL) plays a central role in improving the reasoning and alignment of large language models, yet its efficiency critically depends on how training data are selected. Existing online selection strategies predominantly…

Pairing a lexical retriever with a neural re-ranking model has set state-of-the-art performance on large-scale information retrieval datasets. This pipeline covers scenarios like question answering or navigational queries, however, for…