Search
Search Results
-
Efficient Evaluation of Conjunctive Regular Path Queries Using Multi-way Joins
Recent analyses of real-world queries show that a prominent type of queries is that of conjunctive regular path queries. Despite the increasing...
-
Can Contrastive Learning Refine Embeddings
Recent advancements in contrastive learning have revolutionized self-supervised representation learning and achieved state-of-the-art performance on...
-
Towards Cyber Map** the German Financial System with Knowledge Graphs
The increasing outsourcing by financial intermediaries intensifies the interconnection of the financial system with third-party providers....
-
Generative Expression Constrained Knowledge-Based Decoding for Open Data
In this paper, we present GECKO, a knowledge graph question answering (KGQA) system for data from Statistics Netherlands (Centraal Bureau voor de...
-
SC-Block: Supervised Contrastive Blocking Within Entity Resolution Pipelines
Millions of websites use the schema.org vocabulary to annotate structured data describing products, local businesses, or events within their HTML...
-
Integrating Domain Knowledge for Enhanced Concept Model Explainability in Plant Disease Classification
Deep learning-based plant disease detection has seen promising advancements, particularly in its remarkable ability to identify diseases through...
-
Navigating Ontology Development with Large Language Models
Ontology engineering is a complex and time-consuming task, even with the help of current modelling environments. Often the result is error-prone...
-
Leveraging Pre-trained Language Models for Time Interval Prediction in Text-Enhanced Temporal Knowledge Graphs
Most knowledge graph completion (KGC) methods rely solely on structural information, even though a large number of publicly available KGs contain...
-
OntoEditor: Real-Time Collaboration via Distributed Version Control for Ontology Development
In today’s remote work environment, the demand for real-time collaborative tools has surged. Our research targets efficient collaboration among...
-
Self Contrastive Learning for Session-Based Recommendation
Session-based recommendation, which aims to predict the next item of users’ interest as per an existing sequence interaction of items, has attracted...
-
Investigating the Effects of Sparse Attention on Cross-Encoders
Cross-encoders are effective passage and document re-rankers but less efficient than other neural or classic retrieval models. A few previous studies...
-
Query Obfuscation for Information Retrieval Through Differential Privacy
Protecting the privacy of a user querying an Information Retrieval (IR) system is of utmost importance. The problem is exacerbated when the IR system...
-
A Phrase-Level Attention Enhanced CRF for Keyphrase Extraction
Since sequence labeling-based methods take into account the dependencies between neighbouring labels, they have been widely used for keyphrase...
-
WebSAM-Adapter: Adapting Segment Anything Model for Web Page Segmentation
With the advancement of internet technology, web page segmentation, which aims to divide web pages into semantically coherent units, has become...
-
Lightweight Modality Adaptation to Sequential Recommendation via Correlation Supervision
In Sequential Recommenders (SR), encoding and utilizing modalities in an end-to-end manner is costly in terms of modality encoder sizes. Two-stage...
-
DREQ: Document Re-ranking Using Entity-Based Query Understanding
While entity-oriented neural IR models have advanced significantly, they often overlook a key nuance: the varying degrees of influence individual...
-
VEMO: A Versatile Elastic Multi-modal Model for Search-Oriented Multi-task Learning
Cross-modal search is one fundamental task in multi-modal learning, but there is hardly any work that aims to solve multiple cross-modal search tasks...
-
Eliminating Contextual Bias in Aspect-Based Sentiment Analysis
Pretrained language models (LMs) have made remarkable achievements in aspect-based sentiment analysis (ABSA). However, it is discovered that these...
-
Fine-Tuning CLIP via Explainability Map Propagation for Boosting Image and Video Retrieval
Recent studies have highlighted the remarkable performance of CLIP for diverse downstream tasks. To understand how CLIP performs these tasks, various...
-
Open-Separating Dominating Codes in Graphs
Using dominating sets to separate vertices of graphs is a well-studied problem in the larger domain of identification problems. In such problems, the...