Mehwish Alam
YOU?
Author Swipe
View article: T-REX: Table -- Refute or Entail eXplainer
T-REX: Table -- Refute or Entail eXplainer Open
Verifying textual claims against structured tabular data is a critical yet challenging task in Natural Language Processing with broad real-world impact. While recent advances in Large Language Models (LLMs) have enabled significant progres…
View article: Multilingual Hate Speech Detection Using Meta-Transfer-Learning
Multilingual Hate Speech Detection Using Meta-Transfer-Learning Open
—The fast expansion of online platforms created a record-setting rise in hate speech, undermining safe and wel coming online spaces. This project contributes a multilingual hate speech system based on meta-learning and transfer learning to…
View article: Neurosymbolic Methods for Dynamic Knowledge Graphs
Neurosymbolic Methods for Dynamic Knowledge Graphs Open
Knowledge graphs (KGs) have recently been used for many tools and applications, making them rich resources in structured format. However, in the real world, KGs grow due to the additions of new knowledge in the form of entities and relatio…
View article: Neurosymbolic Methods for Rule Mining
Neurosymbolic Methods for Rule Mining Open
In this chapter, we address the problem of rule mining, beginning with essential background information, including measures of rule quality. We then explore various rule mining methodologies, categorized into three groups: inductive logic …
View article: Refining Wikidata Taxonomy using Large Language Models
Refining Wikidata Taxonomy using Large Language Models Open
Due to its collaborative nature, Wikidata is known to have a complex\ntaxonomy, with recurrent issues like the ambiguity between instances and\nclasses, the inaccuracy of some taxonomic paths, the presence of cycles, and\nthe high level of…
View article: ChitroJera: A Regionally Relevant Visual Question Answering Dataset for Bangla
ChitroJera: A Regionally Relevant Visual Question Answering Dataset for Bangla Open
Visual Question Answer (VQA) poses the problem of answering a natural language question about a visual context. Bangla, despite being a widely spoken language, is considered low-resource in the realm of VQA due to the lack of proper benchm…
View article: BanTH: A Multi-label Hate Speech Detection Dataset for Transliterated Bangla
BanTH: A Multi-label Hate Speech Detection Dataset for Transliterated Bangla Open
The proliferation of transliterated texts in digital spaces has emphasized the need for detecting and classifying hate speech in languages beyond English, particularly in low-resource languages. As online discourse can perpetuate discrimin…
View article: Neurosymbolic Methods for Dynamic Knowledge Graphs
Neurosymbolic Methods for Dynamic Knowledge Graphs Open
Knowledge graphs (KGs) have recently been used for many tools and applications, making them rich resources in structured format. However, in the real world, KGs grow due to the additions of new knowledge in the form of entities and relatio…
View article: Workshop on Deep Learning and Large Language Models for Knowledge Graphs (DL4KG)
Workshop on Deep Learning and Large Language Models for Knowledge Graphs (DL4KG) Open
The use of Knowledge Graphs (KGs) which constitute large networks of real-world entities and their interrelationships, has grown rapidly. A substantial body of research has emerged, exploring the integration of deep learning (DL) and large…
View article: Towards semantically enriched embeddings for knowledge graph completion
Towards semantically enriched embeddings for knowledge graph completion Open
Embedding based Knowledge Graph (KG) completion has gained much attention over the past few years. Most of the current algorithms consider a KG as a multidirectional labeled graph and lack the ability to capture the semantics underlying th…
View article: Neurosymbolic Methods for Rule Mining
Neurosymbolic Methods for Rule Mining Open
In this chapter, we address the problem of rule mining, beginning with essential background information, including measures of rule quality. We then explore various rule mining methodologies, categorized into three groups: inductive logic …
View article: YAGO 4.5: A Large and Clean Knowledge Base with a Rich Taxonomy
YAGO 4.5: A Large and Clean Knowledge Base with a Rich Taxonomy Open
International audience
View article: YAGO 4.5: A Large and Clean Knowledge Base with a Rich Taxonomy
YAGO 4.5: A Large and Clean Knowledge Base with a Rich Taxonomy Open
Knowledge Bases (KBs) find applications in many knowledge-intensive tasks and, most notably, in information retrieval. Wikidata is one of the largest public general-purpose KBs. Yet, its collaborative nature has led to a convoluted schema …
View article: Towards Semantically Enriched Embeddings for Knowledge Graph Completion
Towards Semantically Enriched Embeddings for Knowledge Graph Completion Open
Embedding based Knowledge Graph (KG) Completion has gained much attention over the past few years. Most of the current algorithms consider a KG as a multidirectional labeled graph and lack the ability to capture the semantics underlying th…
View article: Exploring the Impact of Negative Sampling on Patent Citation Recommendation
Exploring the Impact of Negative Sampling on Patent Citation Recommendation Open
pcr_patents.csv is the dataset which is generated by collecting samples randomly from Google Patents by exploiting a Python library. The dataset comprises around 250,000 US patents and their titles, abstracts, and citations. Each patent ha…
View article: NeMig - A Bilingual News Collection and Knowledge Graph about Migration
NeMig - A Bilingual News Collection and Knowledge Graph about Migration Open
NeMig represents a bilingual news collection and knowledge graphs on the topic of migration. The news corpora in German and English were collected from online media outlets from Germany and the US, respectively. NeMIg contains rich textual…
View article: NeMig - A Bilingual News Collection and Knowledge Graph about Migration
NeMig - A Bilingual News Collection and Knowledge Graph about Migration Open
NeMig are two English and German knowledge graphs constructed from news articles on the topic of migration, collected from online media outlets from Germany and the US, respectively. NeMIg contains rich textual and metadata information, su…
View article: NeMig - A Bilingual News Collection and Knowledge Graph about Migration
NeMig - A Bilingual News Collection and Knowledge Graph about Migration Open
NeMig represents a bilingual news collection and knowledge graphs on the topic of migration. The news corpora in German and English were collected from online media outlets from Germany and the US, respectively. NeMIg contains rich textual…
View article: RAILD: Towards Leveraging Relation Features for Inductive Link Prediction In Knowledge Graphs
RAILD: Towards Leveraging Relation Features for Inductive Link Prediction In Knowledge Graphs Open
Due to the open world assumption, Knowledge Graphs (KGs) are never complete. In order to address this issue, various Link Prediction (LP) methods are proposed so far. Some of these methods are inductive LP models which are capable of learn…
View article: Special issue on conceptual structures
Special issue on conceptual structures Open
Funding Open Access funding enabled and organized by Projekt DEAL.
View article: MADLINK: Attentive multihop and entity descriptions for link prediction in knowledge graphs
MADLINK: Attentive multihop and entity descriptions for link prediction in knowledge graphs Open
Knowledge Graphs (KGs) comprise of interlinked information in the form of entities and relations between them in a particular domain and provide the backbone for many applications. However, the KGs are often incomplete as the links between…
View article: Wikidata68K
Wikidata68K Open
Wikidata68K is a benchmark dataset extracted from Wikidata and Wikipedia for inductive link prediction in knowledge graphs.
View article: Wikidata68K
Wikidata68K Open
Wikidata68K is a benchmark dataset extracted from Wikidata and Wikipedia for inductive link prediction in knowledge graphs.
View article: A survey on knowledge-aware news recommender systems
A survey on knowledge-aware news recommender systems Open
News consumption has shifted over time from traditional media to online platforms, which use recommendation algorithms to help users navigate through the large incoming streams of daily news by suggesting relevant articles based on their p…
View article: Entity Type Prediction Leveraging Graph Walks and Entity Descriptions
Entity Type Prediction Leveraging Graph Walks and Entity Descriptions Open
The entity type information in Knowledge Graphs (KGs) such as DBpedia, Freebase, etc. is often incomplete due to automated generation or human curation. Entity typing is the task of assigning or inferring the semantic type of an entity in …
View article: Towards Analyzing the Bias of News Recommender Systems Using Sentiment and Stance Detection
Towards Analyzing the Bias of News Recommender Systems Using Sentiment and Stance Detection Open
News recommender systems are used by online news providers to alleviate\ninformation overload and to provide personalized content to users. However,\nalgorithmic news curation has been hypothesized to create filter bubbles and to\nintensif…
View article: Editorial of the Special Issue on Deep Learning and Knowledge Graphs
Editorial of the Special Issue on Deep Learning and Knowledge Graphs Open
This special issue aims to reinforce the relationships between these communities and foster interdisciplinary research in the areas of KG, Deep Learning, and Natural Language Processing.The works that we have requested from authors should …