Johannes Heinecke

Orange Labs · Natural Language Processing

Knowledge Graph (KG) completion has been excessively studied with a massive number of models proposed for the Link Prediction (LP) task. The main limitation of such models is their insensitivity to time. Indeed, the temporal aspect of stored facts is often ignored. To this end, more and more works consider time as a parameter to complete KGs. In th...

The task of verbalization of RDF triples has known a growth in popularity due to the rising ubiquity of Knowledge Bases (KBs). The formalism of RDF triples is a simple and efficient way to store facts at a large scale. However, its abstract representation makes it difficult for humans to interpret. For this purpose, the WebNLG challenge aims at pro...

This paper describes our recursive system for SemEval-2019 \textit{ Task 1: Cross-lingual Semantic Parsing with UCCA}. Each recursive step consists of two parts. We first perform semantic parsing using a sequence tagger to estimate the probabilities of the UCCA categories in the sentence. Then, we apply a decoding policy which interprets these prob...

We present a spoken conversational question answering proof of concept that is able to answer questions about general knowledge from Wikidata. The dialogue component does not only orchestrate various components but also solve coreferences and ellipsis.

For the purpose of POS tagging noisy user-generated text, should normalization be handled as a preliminary task or is it possible to handle misspelled words directly in the POS tagging model? We propose in this paper a combined approach where some errors are normalized before tagging, while a Gated Recurrent Unit deep neural network based tagger ha...

Le corpus CALOR-Frame est un corpus annoté en cadres sémantiques, constitué de textes encyclopédiques dans le domaine de l'Histoire et produit conjointement par l'Université d'Aix-Marseille et Orange Labs. La constitution de cette ressource s'inscrit dans le cadre général de la recherche d’information avec pour objectif de favoriser l'accès aux con...

Le traitement de l’ambiguïté est un enjeu important pour l’amélioration des performances d’un système de recherche d’information (RI). Les travaux dans ce domaine sont focalisés sur le traitement de l’ambiguïté lexicale par recours à des dictionnaires ou, en recherche d’information multilingue, à des corpus alignés. Mais l’inadéquation de dictionna...

In this article we describe the use of Natural Language Processing platform to inter-pred user queries to be fed into a question-answering system. The advantage of this system is threefold: first, we are able to identify only those requests which correspond to factual questions for which the engine has a precise answer; second, error correction is...

Semantic Web technology is being increasingly applied in a large spectrum of applications in which domain knowledge is conceptualized and formalized (e.g., by means of an ontology) in order to support diversified and automated knowledge processing (e.g., reasoning) performed by a machine. Moreover, through an optimal combination of (cognitive) huma...

Ontologies and natural languages are complementary. Whereas ontologies are used to model knowledge formally, natural language is primarily used by users to communicate with ontology based systems. In order to transform information or queries in natural language into valid ontological expressions, the meaning of natural language entities have to be...

Semantic Web technology is being increasingly applied in a large spectrum of applications in which domain knowledge is conceptualized and formalized (e.g., by means of an ontology) in order to support diversified and automated knowledge processing (e.g., reasoning) performed by a machine. Moreover, through an optimal combination of (cognitive) huma...

Semantic Web technology is being increasingly applied in a large spectrum of applications in which domain knowledge is conceptualized and formalized (e.g., by means of an ontology) in order to support diversified and automated knowledge processing (e.g., reasoning) performed by a machine. Moreover, through an optimal combination of (cognitive) huma...

Ces travaux présentent une extension des représentations formelles pour la sémantique, de l'outil de traitement automatique des langues de Orange Labs1 . Nous abordons ici uniquement des questions relatives à la construction des représentations sémantiques, dans le cadre de l'analyse linguistique. Afin d'obtenir des représentations plus fines de la s...

Cet article décrit une plate-forme de TALN, modulaire et multilingue, enrichie d'un système de contrôle basé sur l'aide multicritère à la décision. La présentation est complétée par une description des données linguistiques utilisées ainsi que des applications basées sur cette technologie. ABSTRACT. This article describes a modular and multilingual...

Cet article décrit une plate-forme de TALN, modulaire et multilingue, enrichie d'un système de contrôle basé sur l'aide multicritère à la décision. La présentation est complétée par une description des données linguistiques utilisées ainsi que des applications basées sur cette technologie. ABSTRACT. This article describes a modular and multilingual...

This article describes a modular & multilingual NLP platform, which is enriched by a system of multicriteria decision-aid. Further we describe the linguistic data used by this platform as well as the applications based on its technology.

In this paper we present an approach that combines multimedia reasoning and natural language processing for the semantic integration of automatic and manual image annotations based on domain ontologies. We discuss how to apply natural language processing to transform natural language descriptions and queries into an ontological representation that...

aceMedia is a 4 year EC part-funded FP6 Integrated Project, ending in December 2007. The project has developed tools to enable users to manage and share both personal and purchased content across PC, STB and mobile platforms. Knowledge-based analysis and ontologies have been successfully exploited in an end-to-end system to enable automated semanti...

Semantic Web technology is being increasingly applied in a large spectrum of applications in which domain knowledge is conceptualized and formalized (e.g., by means of an ontology) in order to support diversified and automated knowledge processing (e.g., reasoning) performed by a machine. Moreover, through an optimal combination of (cognitive) huma...

Résumé Depuis la conception du web sémantique une tâche importante se pose au niveau de traitement automatique du langage : rendre accessible le contenu existant du web dit clas- sique aux traitements et raisonnements ontologiques. Comme la plupart du contenu est composé detextes, onabesoin degénérerdes représentations ontologiquesdeces information...

This paper describes the design and use of the Verbmobil Semantic Database which we developed in order to deal with these issues in the area of lexical semantics in Verbmobil

Natural language parsing is conceived to be a procedure of disambiguation, which successively reduces an initially totally ambiguous structural representation towards a single interpretation. Graded constraints are used as means to express wellformedness conditions of dioeerent strength and to decide which partial structures are locally least prefe...

Natural language parsing is conceived to be a procedure of disambiguation, which successively reduces an initially totally ambiguous structural representation towards a single interpretation. Graded constraints are used as means to express well-formedness conditions of different strength and to decide which partial structures are locally least pref...

8> in+NM Mangor. NM-LN Roedd be-PRETIF-3SG Ioan PRN ym in+NM 1 Johannes Heinecke Mangor. NM-LN "John was in Bangor." "John was (for a while) in Bangor." (9) Bu be-PRETPF-3SG Ioan PRN ym in+NM Mangor NM-LN am for flwyddyn. year-SGSUF "John was in Bangor for one year." (10) Roedd be-PRETIF-3SG Ioan PRN ym in+NM Mangor NM-LN am for flwyddyn. year-SGSU...

this paper is to present and to demonstrate the application of a computer software system creating and maintaining a dictionary of the Chechen and German languages. Currently Chechen language resources can usually only be accessed through the medium of Russian. This may lead to problems especially for linguists who only have a restricted knowledge...

This paper describes the development and use of a lexical semantic database for the Verbmobil speech--to--speech machine translation project. The motivation is to provide a common information source for the distributed development of the semantics, transfer and semantic evaluation modules and to store lexical semantic information application-- inde...

This paper describes the development and use of a lexical semantic database for the Verbmobil speech-to-speech machine translation system. The motivation is to provide a common information source for the distributed development of the semantics, transfer and semantic evaluation modules and to store lexical semantic information application-independe...

This paper describes the design and use of the Verbmobil Semantic Database whichwe developed in order to deal with these issues in the area of lexical semantics inVerbmobil

This paper describes how ontologies are used to mediate between languages and to infer answers to user questions in the multilingual eCommerce mediation system Mkbeem. As an example, the paper discusses on how generic ontologies of colours and materials are used to infer additional facts about clothing products in order to facilitate information ac...

article décrit une plate-forme de TALN, modulaire et multilingue, enrichie d'un système de contrôle basé sur l'aide multicritère à la décision. La présentation est complétée par une description des données linguistiques utilisées ainsi que des applications basées sur cette technologie. ABSTRACT. This article describes a modular and multilingual NLP...

This paper describes how ontologies are used to mediate be-tween languages and to infer answers to user questions in the multilingual e-commerce mediation system mkbeem. 3 As an example, the paper dis-cusses how a complex user request in human language is transformed into an ontological formula and subsequently exploited to identify a ser-vice whic...

Abstract This paper presents our semantic representation whi ch has been introduced in France