Related papers: A categorical error sensitivity index (ISEC): A pr…
Speech command recognition (SCR) has been commonly used on resource constrained devices to achieve hands-free user experience. However, in real applications, confusion among commands with similar pronunciations often happens due to the…
The paper focuses on the interpretability of Grammatical Error Correction (GEC) evaluation metrics, which received little attention in previous studies. To bridge the gap, we introduce **CLEME2.0**, a reference-based metric describing four…
Computational measures of semantic similarity between geographic terms provide valuable support across geographic information retrieval, data mining, and information integration. To date, a wide variety of approaches to geo-semantic…
A Grammatical Error Correction (GEC) system produces a sequence of edits to correct an erroneous sentence. The quality of these edits is typically evaluated against human annotations. However, a sentence may admit multiple valid…
State-of-the-art semantic segmentation models are typically optimized in a data-driven fashion, minimizing solely per-pixel or per-segment classification objectives on their training data. This purely data-driven paradigm often leads to…
Data imputation has been extensively explored to solve the missing data problem. The dramatically increasing volume of incomplete data makes the imputation models computationally infeasible in many real-life applications. In this paper, we…
We propose the Signal Dice Similarity Coefficient (SDSC), a structure-aware metric function for time series self-supervised representation learning. Most Self-Supervised Learning (SSL) methods for signals commonly adopt distance-based…
The modernization of existing and new nuclear power plants with digital instrumentation and control systems (DI&C) is a recent and highly trending topic. However, there lacks strong consensus on best-estimate reliability methodologies by…
Taking inspiration from Set Theory, we introduce SetCSE, an innovative information retrieval framework. SetCSE employs sets to represent complex semantics and incorporates well-defined operations for structured information querying under…
Continuously learning new classes without catastrophic forgetting is a challenging problem for on-device acoustic event classification given the restrictions on computation resources (e.g., model size, running memory). To alleviate such an…
Handling implicit language is essential for natural language processing systems to achieve precise text understanding and facilitate natural interactions with users. Despite its importance, the absence of a metric for accurately measuring…
Information-theoretic quantities play a crucial role in understanding non-linear relationships between random variables and are widely used across scientific disciplines. However, estimating these quantities remains an open problem,…
Incremental or continual learning has been extensively studied for image classification tasks to alleviate catastrophic forgetting, a phenomenon that earlier learned knowledge is forgotten when learning new concepts. For class incremental…
Assembly state recognition facilitates the execution of assembly procedures, offering feedback to enhance efficiency and minimize errors. However, recognizing assembly states poses challenges in scalability, since parts are frequently…
In semantic segmentation, even state-of-the-art deep learning models fall short of the performance required in certain high-stakes applications such as medical image analysis. In these cases, performance can be improved by allowing a model…
Although Large language Model (LLM)-powered information extraction (IE) systems have shown impressive capabilities, current fine-tuning paradigms face two major limitations: high training costs and difficulties in aligning with LLM…
Item categorization is a machine learning task which aims at classifying e-commerce items, typically represented by textual attributes, to their most suitable category from a predefined set of categories. An accurate item categorization…
With the help of powerful generative models, Semantic Image Compression (SIC) has achieved impressive performance at ultra-low bitrate. However, due to coarse-grained visual-semantic alignment and inherent randomness, the reliability of SIC…
Incremental semantic segmentation aims to continually learn the segmentation of new coming classes without accessing the training data of previously learned classes. However, most current methods fail to address catastrophic forgetting and…
The Half-Trek Criterion (HTC) is the primary graphical tool for determining generic identifiability of causal effect coefficients in linear structural equation models (SEMs) with latent confounders. However, HTC is inherently node-wise: it…