Search Results for author: Mehwish Alam

Found 15 papers, 6 papers with code

NeMig -- A Bilingual News Collection and Knowledge Graph about Migration

1 code implementation1 Sep 2023 Andreea Iana, Mehwish Alam, Alexander Grote, Nevena Nikolajevic, Katharina Ludwig, Philipp Müller, Christof Weinhardt, Heiko Paulheim

News recommendation plays a critical role in shaping the public's worldviews through the way in which it filters and disseminates information about different topics.

Benchmarking Knowledge Graphs +1

Integrating the Wikidata Taxonomy into YAGO

1 code implementation23 Aug 2023 Fabian Suchanek, Mehwish Alam, Thomas Bonald, Pierre-Henri Paris, Jules Soria

Wikidata is one of the largest public general-purpose Knowledge Bases (KBs).

Towards Semantically Enriched Embeddings for Knowledge Graph Completion

no code implementations31 Jul 2023 Mehwish Alam, Frank van Harmelen, Maribel Acosta

Most of the current algorithms consider a KG as a multidirectional labeled graph and lack the ability to capture the semantics underlying the schematic information.

Inductive Link Prediction Knowledge Graph Completion +1

RAILD: Towards Leveraging Relation Features for Inductive Link Prediction In Knowledge Graphs

1 code implementation21 Nov 2022 Genet Asefa Gesese, Harald Sack, Mehwish Alam

In this work, a novel Relation Aware Inductive Link preDiction (RAILD) is proposed for KG completion which learns representations for both unseen entities and unseen relations.

Inductive Link Prediction Knowledge Graphs +1

A Knowledge Graph Embeddings based Approach for Author Name Disambiguation using Literals

1 code implementation24 Jan 2022 Cristian Santini, Genet Asefa Gesese, Silvio Peroni, Aldo Gangemi, Harald Sack, Mehwish Alam

These efforts to standardize these data and make them accessible have also led to many challenges such as exploration of scholarly articles, ambiguous authors, etc.

Blocking Knowledge Graph Embeddings +1

On the Impact of Temporal Representations on Metaphor Detection

1 code implementation LREC 2022 Giorgio Ottolina, Matteo Palmonari, Mehwish Alam, Manuel Vimercati

To the best of our knowledge, this is the first study that examines the metaphor detection task with a detailed exploratory analysis where different temporal and static word embeddings are used to account for different representations of literal meanings.

Word Embeddings

MigrationsKB: A Knowledge Base of Public Attitudes towards Migrations and their Driving Factors

1 code implementation17 Aug 2021 Yiyi Chen, Harald Sack, Mehwish Alam

The goal of this study is the analysis of social media platform to quantify public attitudes towards migrations and the identification of different factors causing these attitudes.

Entity Linking Hate Speech Detection +1

Entity Type Prediction in Knowledge Graphs using Embeddings

no code implementations28 Apr 2020 Russa Biswas, Radina Sofronova, Mehwish Alam, Harald Sack

Open Knowledge Graphs (such as DBpedia, Wikidata, YAGO) have been recognized as the backbone of diverse applications in the field of data mining and information retrieval.

Entity Typing Information Retrieval +5

Is Aligning Embedding Spaces a Challenging Task? A Study on Heterogeneous Embedding Alignment Methods

no code implementations21 Feb 2020 Russa Biswas, Mehwish Alam, Harald Sack

Representation Learning of words and Knowledge Graphs (KG) into low dimensional vector spaces along with its applications to many real-world scenarios have recently gained momentum.

Entity Disambiguation Question Answering +1

A Survey on Knowledge Graph Embeddings with Literals: Which model links better Literal-ly?

no code implementations28 Oct 2019 Genet Asefa Gesese, Russa Biswas, Mehwish Alam, Harald Sack

This paper conducts a survey of KG embedding models which not only consider the structured information contained in the form of entities and relations in a KG but also the unstructured information represented as literals such as text, numerical values, images, etc.

Entity Linking Knowledge Graph Embeddings +4

Semantic Role Labeling for Knowledge Graph Extraction from Text

no code implementations4 Nov 2018 Mehwish Alam, Aldo Gangemi, Valentina Presutti, Diego Reforgiato Recupero

This paper introduces TakeFive, a new semantic role labeling method that transforms a text into a frame-oriented knowledge graph.

Dependency Parsing Semantic Role Labeling

Amnestic Forgery: an Ontology of Conceptual Metaphors

no code implementations30 May 2018 Aldo Gangemi, Mehwish Alam, Valentina Presutti

This paper presents Amnestic Forgery, an ontology for metaphor semantics, based on MetaNet, which is inspired by the theory of Conceptual Metaphor.

Cannot find the paper you are looking for? You can Submit a new open access paper.