no code implementations • ACL 2017 • Paramita Mirza, Simon Razniewski, Fariz Darari, Gerhard Weikum
Information extraction (IE) from text has largely focused on relations between individual entities, such as who has won which award.
no code implementations • 20 Sep 2017 • Simon Razniewski, Vevake Balaraman, Werner Nutt
In this work, we have developed a human-annotated dataset of 350 preference judgments among pairs of knowledge base properties for fixed entities.
1 code implementation • 10 Jul 2018 • Paramita Mirza, Simon Razniewski, Fariz Darari, Gerhard Weikum
In a large-scale experiment, we demonstrate the potential for knowledge base enrichment by applying CINEX to 2, 474 frequent relations in Wikidata.
no code implementations • 29 Jan 2019 • Cuong Xuan Chu, Simon Razniewski, Gerhard Weikum
Taxonomies are important building blocks of structured knowledge bases, and their construction from text sources and Wikipedia has received much attention.
2 code implementations • 27 May 2019 • Julien Romero, Simon Razniewski, Koninika Pal, Jeff Z. Pan, Archit Sakhadeo, Gerhard Weikum
Commonsense knowledge about object properties, human behavior and general concepts is crucial for robust AI applications.
no code implementations • 2 Sep 2019 • Sreyasi Nag Chowdhury, Simon Razniewski, Gerhard Weikum
Multimodal contents have become commonplace on the Internet today, manifested as news articles, social media posts, and personal or business blog posts.
no code implementations • IJCNLP 2019 • Simon Razniewski, Nitisha Jain, Paramita Mirza, Gerhard Weikum
Scalar implicatures are language features that imply the negation of stronger statements, e. g., {``}She was married twice{''} typically implicates that she was not married thrice.
no code implementations • 13 Jan 2020 • Hiba Arnaout, Simon Razniewski, Gerhard Weikum, Jeff Z. Pan
Negative statements are useful to overcome limitations of question answering systems that are mainly geared for positive questions; they can also contribute to informative summaries of entities.
1 code implementation • AKBC 2020 • Yohan Chalier, Simon Razniewski, Gerhard Weikum
Each concept is treated in isolation from other concepts, and the only quantitative measure (or ranking) of properties is a confidence score that the statement is valid.
no code implementations • AKBC 2020 • Hiba Arnaout, Simon Razniewski, Gerhard Weikum
Negative statements would be important to overcome current limitations of question answering, yet due to their potential abundance, any effort towards compiling them needs a tight coupling with ranking.
1 code implementation • 6 Mar 2020 • Shrestha Ghosh, Simon Razniewski, Gerhard Weikum
This paper focuses on set-valued predicates, i. e., the relationship between an entity and a set of entities.
1 code implementation • 7 May 2020 • Shrestha Ghosh, Simon Razniewski, Gerhard Weikum
Predicate constraints of general-purpose knowledge bases (KBs) like Wikidata, DBpedia and Freebase are often limited to subproperty, domain and range constraints.
no code implementations • 12 May 2020 • Diego Calvanese, Julien Corman, Davide Lanti, Simon Razniewski
Counting answers to a query is an operation supported by virtually all database management systems.
no code implementations • 24 Sep 2020 • Gerhard Weikum, Luna Dong, Simon Razniewski, Fabian Suchanek
Equipping machines with comprehensive knowledge of the world's entities and their relationships has been a long-standing goal of AI.
no code implementations • EMNLP 2020 • Cuong Xuan Chu, Simon Razniewski, Gerhard Weikum
Fiction and fantasy are archetypes of long-tail domains that lack suitable NLP methodologies and tools.
1 code implementation • 2 Nov 2020 • Tuan-Phong Nguyen, Simon Razniewski, Gerhard Weikum
Prior works like ConceptNet, TupleKB and others compiled large CSK collections, but are restricted in their expressiveness to subject-predicate-object (SPO) triples with simple concepts for S and monolithic strings for P and O.
no code implementations • 4 Mar 2021 • Simon Razniewski, Niket Tandon, Aparna S. Varde
Commonsense knowledge is a foundational cornerstone of artificial intelligence applications.
no code implementations • EACL 2021 • Sreyasi Nag Chowdhury, Simon Razniewski, Gerhard Weikum
The Internet contains a multitude of social media posts and other of stories where text is interspersed with images.
no code implementations • 5 May 2021 • Simon Razniewski
Compiling commonsense knowledge is traditionally an AI topic approached by manual labor.
no code implementations • ACL 2021 • Tuan-Phong Nguyen, Simon Razniewski, Gerhard Weikum
ASCENT is a fully automated methodology for extracting and consolidating commonsense assertions from web contents (Nguyen et al., WWW 2021).
no code implementations • AKBC 2021 • Cuong Xuan Chu, Simon Razniewski, Gerhard Weikum
Knowledge base construction has recently been extended to fictional domains like multi-volume novels and TV/movie series, aiming to support explorative queries for fans and sub-culture studies by humanities researchers.
Cultural Vocal Bursts Intensity Prediction Relation Extraction
no code implementations • 10 Oct 2021 • Simon Razniewski, Andrew Yates, Nora Kassner, Gerhard Weikum
Pre-trained language models (LMs) have recently gained attention for their potential as an alternative to (or proxy for) explicit knowledge bases (KBs).
no code implementations • 26 Nov 2021 • Sneha Singhania, Simon Razniewski, Gerhard Weikum
We employ methods combining features with statistical models like TF-IDF and language models like BERT.
1 code implementation • 30 Nov 2021 • Tuan-Phong Nguyen, Simon Razniewski, Julien Romero, Gerhard Weikum
However, they are restricted in their expressiveness to subject-predicate-object (SPO) triples with simple concepts for S and strings for P and O.
no code implementations • CSRR (ACL) 2022 • Tuan-Phong Nguyen, Simon Razniewski
Starting from the COMET methodology by Bosselut et al. (2019), generating commonsense knowledge directly from pre-trained language models has recently received significant attention.
1 code implementation • 11 Apr 2022 • Shrestha Ghosh, Simon Razniewski, Gerhard Weikum
A challenging case in web search and question answering are count queries, such as \textit{"number of songs by John Lennon"}.
no code implementations • 19 Aug 2022 • Hiba Arnaout, Simon Razniewski, Gerhard Weikum, Jeff Z. Pan
This way, positive statements about comparable concepts that are absent for the target concept become seeds for negative statement candidates.
1 code implementation • 15 Sep 2022 • Shrestha Ghosh, Simon Razniewski, Gerhard Weikum
In this work we address the challenging case of answering count queries in web search, such as ``number of songs by John Lennon''.
no code implementations • 10 Oct 2022 • Julien Romero, Simon Razniewski
Compiling comprehensive repositories of commonsense knowledge is a long-standing problem in AI.
2 code implementations • 14 Oct 2022 • Tuan-Phong Nguyen, Simon Razniewski, Aparna Varde, Gerhard Weikum
Commonsense knowledge, which is crucial for robust human-centric AI, is covered by a small number of structured knowledge projects.
no code implementations • 2 Nov 2022 • Suhas Shrinivasan, Simon Razniewski
The inevitability of change in the real-world, brings us to a central property of KBs -- they are highly dynamic in that the information they contain are constantly subject to change.
1 code implementation • 8 Mar 2023 • Shrestha Ghosh, Simon Razniewski, Gerhard Weikum
Questions on class cardinality comparisons are quite tricky to answer and come with its own challenges.
1 code implementation • 20 Mar 2023 • Blerta Veseli, Sneha Singhania, Simon Razniewski, Gerhard Weikum
In a second step, we perform a human evaluation on predictions that are not yet in the KB, as only this provides real insights into the added value over existing KBs.
no code implementations • 9 May 2023 • Simon Razniewski, Hiba Arnaout, Shrestha Ghosh, Fabian Suchanek
General-purpose knowledge bases (KBs) are a cornerstone of knowledge-centric AI.
no code implementations • 26 May 2023 • Hiba Arnaout, Simon Razniewski
We examine the ability of large language models (LLMs) to generate salient (interesting) negative statements about real-world entities; an emerging research topic of the last few years.
1 code implementation • 22 Jun 2023 • Julien Romero, Simon Razniewski
Structured knowledge bases (KBs) are the backbone of many know\-ledge-intensive applications, and their automated construction has received considerable attention.
1 code implementation • 30 Jun 2023 • Lihu Chen, Simon Razniewski, Gerhard Weikum
To evaluate our method and various baselines, we introduce a novel dataset, called MALT, rooted in Wikidata.
1 code implementation • 6 Jul 2023 • Sneha Singhania, Simon Razniewski, Gerhard Weikum
The widespread usage of latent language representations via pre-trained language models (LMs) suggests that they are a promising source of structured knowledge.
no code implementations • 11 Aug 2023 • Jeff Z. Pan, Simon Razniewski, Jan-Christoph Kalo, Sneha Singhania, Jiaoyan Chen, Stefan Dietze, Hajira Jabeen, Janna Omeliyanenko, Wen Zhang, Matteo Lissandrini, Russa Biswas, Gerard de Melo, Angela Bonifati, Edlira Vakaj, Mauro Dragoni, Damien Graux
Large Language Models (LLMs) have taken Knowledge Representation -- and the world -- by storm.
no code implementations • 23 Oct 2023 • Blerta Veseli, Simon Razniewski, Jan-Christoph Kalo, Gerhard Weikum
Structured knowledge bases (KBs) are an asset for search engines and other applications, but are inevitably incomplete.
no code implementations • 3 Nov 2023 • Valentin Knappich, Simon Razniewski, Annemarie Friedrich
We furthermore show that the hyperparameter $\lambda$ in token-level loss weights can be used to control the edit distance and the simplicity level (FKGL).
1 code implementation • 11 Dec 2023 • Timo Pierre Schrader, Simon Razniewski, Lukas Lange, Annemarie Friedrich
Understanding causality is a core aspect of intelligence.
no code implementations • 16 Feb 2024 • Tuan-Phong Nguyen, Simon Razniewski, Gerhard Weikum
Despite recent progress, large language models (LLMs) still face the challenge of appropriately reacting to the intricacies of social and cultural conventions.
no code implementations • SALLD (LREC) 2022 • Brad McNamee, Aparna Varde, Simon Razniewski
We present commonsense interpretations of results, such that they are not impervious to the masses.
no code implementations • EACL (LANTERN) 2021 • Sreyasi Nag Chowdhury, Rajarshi Bhowmik, Hareesh Ravi, Gerard de Melo, Simon Razniewski, Gerhard Weikum
Modern web content - news articles, blog posts, educational resources, marketing brochures - is predominantly multimodal.