Related papers: SHINE: Syntax-augmented Hierarchical Interactive E…

Cross-lingual transfer between a high-resource language and its dialects or closely related language varieties should be facilitated by their similarity. However, current approaches that operate in the embedding space do not take surface…

Information extraction suffers from its varying targets, heterogeneous structures, and demand-specific schemas. In this paper, we propose a unified text-to-structure generation framework, namely UIE, which can universally model different IE…

Many early neural Information Retrieval (NeurIR) methods are re-rankers that rely on a traditional first-stage retriever due to expensive query time computations. Recently, representation-based retrievers have gained much attention, which…

Extracting fine-grained experimental findings from literature can provide dramatic utility for scientific applications. Prior work has developed annotation schemas and datasets for limited aspects of this problem, failing to capture the…

Robust multi-view learning with incomplete information has received significant attention due to issues such as incomplete correspondences and incomplete instances that commonly affect real-world multi-view applications. Existing approaches…

Self-supervised vision-language models trained with contrastive objectives form the basis of current state-of-the-art methods in AI vision tasks. The success of these models is a direct consequence of the huge web-scale datasets used to…

This paper introduces {HINER}, a novel neural representation for compressing HSI and ensuring high-quality downstream tasks on compressed HSI. HINER fully exploits inter-spectral correlations by explicitly encoding of spectral wavelengths…

A proper semantic representation for encoding side information is key to the success of zero-shot learning. In this paper, we explore two alternative semantic representations especially for zero-shot human action recognition: textual…

Traditional sequence-to-sequence (seq2seq) models and other variations of the attention-mechanism such as hierarchical attention have been applied to the text summarization problem. Though there is a hierarchy in the way humans use language…

In order to improve future network performance, this paper proposes scalable intelligence-enabled networking (SIEN) with eliminating traffic redundancy for audio-visual-tactile Internet in 5G scenarios such as enhanced mobile broadband,…

The development of deep learning models in medical image analysis is majorly limited by the lack of large-sized and well-annotated datasets. Unsupervised learning does not require labels and is more suitable for solving medical image…

In Natural Language (NL) applications, there is often a mismatch between what the NL interface is capable of interpreting and what a lay user knows how to express. This work describes a novel natural language interface that reduces this…

This paper introduces BMIKE-53, a comprehensive benchmark for cross-lingual in-context knowledge editing (IKE) across 53 languages, unifying three knowledge editing (KE) datasets: zsRE, CounterFact, and WikiFactDiff. Cross-lingual KE, which…

Existing zero-shot learning (ZSL) models typically learn a projection function from a feature space to a semantic embedding space (e.g.~attribute space). However, such a projection function is only concerned with predicting the training…

Electronic Health Records (EHRs) hold immense potential for advancing healthcare, offering rich, longitudinal data that combines structured information with valuable insights from unstructured clinical notes. However, the unstructured…

Zero-shot composed image retrieval (ZS-CIR), which takes a textual modification and a reference image as a query to retrieve a target image without triplet labeling, has gained more and more attention in data mining. Current ZS-CIR research…

With the great success of networks, it witnesses the increasing demand for the interpretation of the internal network mechanism, especially for the net decision-making logic. To tackle the challenge, the Concept-harmonized HierArchical…

Key Information Extraction (KIE) is a challenging multimodal task that aims to extract structured value semantic entities from visually rich documents. Although significant progress has been made, there are still two major challenges that…

Temporal grounding, also known as video moment retrieval, aims at locating video segments corresponding to a given query sentence. The compositional nature of natural language enables the localization beyond predefined events, posing a…

User-defined keyword spotting on a resource-constrained edge device is challenging. However, keywords are often bounded by a maximum keyword length, which has been largely under-leveraged in prior works. Our analysis of keyword-length…