1 code implementation • NAACL (ACL) 2022 • Anastasia Shimorina, Johannes Heinecke, Frédéric Herledan
This paper presents an effort within our company of developing knowledge extraction pipeline for English, which can be further used for constructing an entreprise-specific knowledge base.
no code implementations • INLG (ACL) 2020 • Imen Akermi, Johannes Heinecke, Frédéric Herledan
This paper explores Natural Language Generation within the context of Question-Answering task.
no code implementations • CLTW (LREC) 2022 • Johannes Heinecke, Anastasia Shimorina
Deep Semantic Parsing into Abstract Meaning Representation (AMR) graphs has reached a high quality with neural-based seq2seq approaches.
no code implementations • JEP/TALN/RECITAL 2022 • Rim Abrougui, Géraldine Damnati, Johannes Heinecke, Frédéric Béchet
La tâche de compréhension automatique du langage en contexte d’interaction (NLU pour Natural Language Understanding) est souvent réduite à la détection d’intentions et de concepts sur des corpus mono-domaines annotés avec une seule intention par énoncé.
no code implementations • NAACL (SUKI) 2022 • Sebastien Montella, Lina Rojas-Barahona, Frederic Bechet, Johannes Heinecke, Alexis Nasr
In general, QA systems query a Knowledge Base (KB) to detect and extract the raw answers as final prediction.
no code implementations • 12 Feb 2023 • Sebastien Montella, Alexis Nasr, Johannes Heinecke, Frederic Bechet, Lina M. Rojas-Barahona
Text generation from Abstract Meaning Representation (AMR) has substantially benefited from the popularized Pretrained Language Models (PLMs).
no code implementations • Findings (ACL) 2021 • Sebastien Montella, Lina Rojas-Barahona, Johannes Heinecke
We further propose Hercules, a time-aware extension of AttH model, which defines the curvature of a Riemannian manifold as the product of both relation and time.
no code implementations • ACL (WebNLG, INLG) 2020 • Sebastien Montella, Betty Fabre, Tanguy Urvoy, Johannes Heinecke, Lina Rojas-Barahona
The task of verbalization of RDF triples has known a growth in popularity due to the rising ubiquity of Knowledge Bases (KBs).
no code implementations • WS 2020 • Johannes Heinecke
Then, we use a set of linguistic rules which generate the enhanced dependencies for the syntactic tree.
no code implementations • JEPTALNRECITAL 2020 • Imen Akermi, Johannes Heinecke, Fr{\'e}d{\'e}ric Herledan
Cet article pr{\'e}sente une approche non-supervis{\'e}e bas{\'e}e sur les mod{\`e}les Transformer pour la g{\'e}n{\'e}ration du langage naturel dans le cadre des syst{\`e}mes de question-r{\'e}ponse.
no code implementations • LREC 2020 • Delphine Charlet, Geraldine Damnati, Frederic Bechet, Gabriel Marzinotto, Johannes Heinecke
Machine Reading received recently a lot of attention thanks to both the availability of very large corpora such as SQuAD or MS MARCO containing triplets (document, question, answer), and the introduction of Transformer Language Models such as BERT which obtain excellent results, even matching human performance according to the SQuAD leaderboard.
no code implementations • WS 2019 • Frederic Bechet, Cindy Aloui, Delphine Charlet, Geraldine Damnati, Johannes Heinecke, Alexis Nasr, Frederic Herledan
Machine reading comprehension is a task related to Question-Answering where questions are not generic in scope but are related to a particular document.
no code implementations • SEMEVAL 2019 • Gabriel Marzinotto, Johannes Heinecke, Geraldine Damnati
Parsing is done recursively, we perform a first inference on the sentence to extract the main scenes and links and then we recursively apply our model on the sentence using a masking feature that reflects the decisions made in previous steps.
no code implementations • WS 2019 • Lina M. Rojas-Barahona, Pascal Bellec, Benoit Besset, Martinho Dos-Santos, Johannes Heinecke, Munshi Asadullah, Olivier Le-Blouch, Jean Y. Lancien, Géraldine Damnati, Emmanuel Mory, Frédéric Herledan
We present a spoken conversational question answering proof of concept that is able to answer questions about general knowledge from Wikidata.
no code implementations • JEPTALNRECITAL 2019 • Frederic Bechet, Cindy Aloui, Delphine Charlet, Geraldine Damnati, Johannes Heinecke, Alexis Nasr, Frederic Herledan
Le but de cette {\'e}tude est de permettre le d{\'e}veloppement de telles ressources pour d{'}autres langues {\`a} moindre co{\^u}t en proposant une m{\'e}thode g{\'e}n{\'e}rant de mani{\`e}re semi-automatique des questions {\`a} partir d{'}une analyse s{\'e}mantique d{'}un grand corpus.
no code implementations • CONLL 2017 • Johannes Heinecke, Munshi Asadullah
This paper describes the system of the Team Orange-Deski{\~n}, used for the CoNLL 2017 UD Shared Task in Multilingual Dependency Parsing.