Research

Babelscape is committed to carrying out research and develop technological innovation at the highest level in the field of multilingual Natural Language Understanding with a strong emphasis on neuro-symbolic approaches which combine knowledge graphs with deep learning models.


All Babelscape products are the result of important investments in Research & Development (R&D), which are covered by the following macro-projects:

  • Semantic Natural Language Understanding: probably the most central goal of our company is to devise novel approaches that can determine the meaning of texts independently of the language they are written in, by associating words and phrases with concepts (Word Sense Disambiguation), entities (entity linking), predicates and their arguments (Semantic Role Labeling), the meaning structure formalisms (semantic parsing) etc.
  • Personalizable Multilingual Knowledge Graphs, by creating large multilingual domain-oriented or need-oriented knowledge graphs starting from datasets and term banks.
  • TraDeInterpret, where we enable the semantic interpretation of strings (trademarks) across all EU languages depending on the Nice classes and the Goods & Services description of the trademark.
  • KnowGraphs, a scientific project involving 15 Early-Stage Researchers, 2 of which are Babelscape's employees (see below).

Babelscape is currently funding 5 industrial PhD positions for its employees based on agreements with the Sapienza University of Rome to carry out research.

Scientific Projects

Babelscape is involved in cutting-edge research projects, including the following EU-funded Initial Training Network:

KnowGraphs logo

KnowGraphs

Knowledge graphs (KGs) are a flexible knowledge representation paradigm intended to allow knowledge to be consumed by humans and machines. KGs are widely regarded as a key enabler for a number of increasingly popular technologies including Web search, question answering, personal assistants and AI across most sectors including Industry 4.0, personalized medicine, legislation, economics and more. KGs are now used by several large companies as a key component of their data products. However, while they are rightly praised as a key technology for all future data-driven enterprises and regarded as a promising approach towards “blurring the lines between human and machine”, KGs are currently unattainable for the majority of companies and users.

https://knowgraphs.eu/

Publications

Abelardo Carlos Martìnez Lorenzo, Marco Maru, Roberto Navigli
Fully-Semantic Parsing and Generation: the BabelNet Meaning Representation
Proceedings of ACL 2022
Simone Tedeschi, Federico Martelli, Roberto Navigli
ID10M: Idiom Identification in 10 Languages
Findings of NAACL 2022
Simone Tedeschi, Roberto Navigli
NER4ID at SemEval-2022 Task 2: Named Entity Recognition for Idiomaticity Detection
Proceedings of SemEval 2022
Roberto Navigli, Rexhina Blloshmi, Abelardo Carlos Martìnez Lorenzo
BabelNet Meaning Representation: A Fully Semantic Formalism to Overcome Language Barriers
Proceedings of AAAI-22
Pere-Lluis Huguet Cabot, Roberto Navigli
REBEL: Relation Extraction By End-to-end Language generation
Findings of EMNLP 2021: pp. 2370-2381
Rexhina Blloshmi, Michele Bevilacqua, Edoardo Fabiano, Valentina Caruso, Roberto Navigli
SPRING Goes Online: End-to-End AMR Parsing and Generation
Proceedings of EMNLP 2021: pp. 134-142
Simone Conia, Riccardo Orlando, Fabrizio Brignone, Francesco Cecconi, Roberto Navigli
InVeRo-XL: Making Cross-Lingual Semantic Role Labeling Accessible with Intelligible Verbs and Roles
Proceedings of EMNLP 2021: pp. 319-328
Riccardo Orlando, Simone Conia, Fabrizio Brignone, Francesco Cecconi, Roberto Navigli
AMuSE-WSD: An All-in-one Multilingual System for Easy Word Sense Disambiguation
Proceedings of EMNLP 2021: pp. 329-307
Simone Tedeschi, Simone Conia, Francesco Cecconi, Roberto Navigli
Named Entity Recognition for Entity Linking: What Works and What's Next
Findings of EMNLP 2021: pp. 2584-2596
Simone Tedeschi, Valentino Maiorca, Niccolò Campolungo, Francesco Cecconi, Roberto Navigli
WikiNEuRal: Combined Neural and Knowledge-based Silver Data Creation for Multilingual NER
Findings of EMNLP 2021: pp. 2521-2533
Roberto Navigli, Michele Bevilacqua, Simone Conia, Dario Montagnini, Francesco Cecconi
Ten Years of BabelNet: A Survey
Proceedings of IJCAI 2021: pp. 4559-4567
Pere-Lluís Huget Cabot, David Abadi, Agneta Fischer, Ekaterina Shutova
Us vs. Them: A Dataset of Populist Attitudes, News Bias and Emotions
Proceedings of EACL 2021: pp. 1921-1945
Simone Conia, Fabrizio Brignone, Davide Zanfardino, Roberto Navigli
InVeRo: Making Semantic Role Labeling Accessible with Intelligible Verbs and Roles
Proceedings of EMNLP 2020: pp. 77-84
Federico Scozzafava, Marco Maru, Fabrizio Brignone, Giovanni Torrisi, Roberto Navigli
Personalized PageRank with Syntagmatic Information for Multilingual Word Sense Disambiguation
Proceedings of ACL 2020: pp. 37-46
Marco Maru, Federico Scozzafava, Federico Martelli, Roberto Navigli
SyntagNet: Challenging Supervised Word Sense Disambiguation with Lexical-Semantic Combinations
Proceedings of EMNLP/IJCNLP 2019: pp. 3532-3538

Contact Us

Thank you for your interest in Babelscape. Please fill out this inquiry form to receive more information about our products.

Send