Commonsense Properties from Query Logs and Question Answering Forums
- Julien Romero, Simon Razniewski, K. Pal, Jeff Z. Pan, Archit Sakhadeo, G. Weikum
- Computer ScienceInternational Conference on Information and…
- 27 May 2019
Quasimodo, a methodology and tool suite for distilling commonsense properties from non-standard web sources that focuses on salient properties that are typically associated with certain objects or concepts, is presented.
Inside Quasimodo: Exploring Construction and Usage of Commonsense Knowledge
- Julien Romero, Simon Razniewski
- Computer ScienceInternational Conference on Information and…
- 19 October 2020
A companion web portal is presented which allows to explore the data, to run and analyze the extraction pipeline live, and to inspect the usage of Quasimodo's knowledge in several downstream use cases.
Refined Commonsense Knowledge from Large-Scale Web Contents
- Tuan-Phong Nguyen, S. Razniewski, Julien Romero, G. Weikum
- Computer ScienceIEEE Transactions on Knowledge and Data…
- 30 November 2021
This paper presents a method called A SCENT ++ to automatically build a large-scale knowledge base (KB) of CSK assertions, with refined expressiveness and both better precision and recall than prior works.
Pyformlang: An Educational Library for Formal Language Manipulation
- Julien Romero
- Computer Science, EducationTechnical Symposium on Computer Science Education
- 3 March 2021
This tool paper introduces Pyformlang, a practical and pedagogical Python library for formal languages, which implements the most common algorithms of the domain, accessible by an easy-to-use interface.
Equivalent Rewritings on Path Views with Binding Patterns
- Julien Romero, N. Preda, A. Amarilli, Fabian M. Suchanek
- Computer ScienceExtended Semantic Web Conference
- 16 March 2020
It is shown how queries can be rewritten into equivalent execution plans, which are guaranteed to deliver the same results as the query on all databases, and how this method can be used to answer queries on real-world Web services.
Plug and Play Post-Stack Seismic Inversion with CNN-Based Denoisers
- Julien Romero, M. Corrales, N. Luiken, M. Ravasi
- GeologySecond EAGE Subsurface Intelligence Workshop
- 2022
Computing and Illustrating Query Rewritings on Path Views with Binding Patterns
- Julien Romero, N. Preda, A. Amarilli, Fabian M. Suchanek
- Computer ScienceInternational Conference on Information and…
- 19 October 2020
This system demonstration investigates how to use views with binding patterns, which are a formalization of REST Web services, to answer a complex user query, by rewriting it as an execution plan, i.e., an orchestration of calls to the views.
Harvesting commonsense and hidden knowledge from web services. (Collecte de connaissances cachées et du sens commun à partir de services web)
- Julien Romero
- Computer Science
- 2020
Abstractive Text Summarisation with Neural Networks
- Julien Romero
- Computer Science
- 2017
This paper presents a meta-modelling framework that automates the very labor-intensive and therefore time-heavy and expensive and expensive process of manually cataloging text in order to derive text summary values.
Query Rewriting On Path Views Without Integrity Constraints
- Julien Romero, N. Preda, Fabian M. Suchanek
- Computer ScienceDataMod@CIKM
- 7 October 2020
This paper describes a class of plans that give practical guarantees about their result even if there are no integrity constraints and provides a characterisation of such plans and a complete and correct algorithm to enumerate them.