h-farm innovation becomes maize
h-farm innovation becomes maize
h-farm innovation becomes maize
h-farm innovation becomes maize
h-farm innovation becomes maize
h-farm innovation becomes maize
h-farm innovation becomes maize
h-farm innovation becomes maize
h-farm innovation becomes maize
h-farm innovation becomes maize
h-farm innovation becomes maize
H-FARM Innovation becomes MAIZE.
It’s still us: same spirit, but new ambitions
and a different name.
Check out our new website.

CELI is H-FARM Innovation’s lab for language technology

We provide expertise, research, and tools for the improvement of business through Natural Language Processing technologies.

CELI was founded in 1999 as a research center for language computation. Over the years, it has become a consultancy company focused on using AI & NLP. Our goal is to extract knowledge and create value through language-related data.


In 2021, all the services of CELI have joined H-FARM Innovation’s consulting offering.

Points of view and future scenarios

Our thoughts about Language Technology and its applications

Our tools

Personalized customer relationships and data-driven decisions

CELI has developed software tools that leverage Natural Language Processing and Deep Learning technologies to help organizations understand user needs and, consequently, provide faster, more accurate and effective responses. is a Text Analysis platform which, through linguistic analysis and Machine Learning algorithms, allows you to understand linguistic data (text and voice) to extract information, identifying the most frequent or relevant topics, sentiment and opinions and classifying the texts according to their content.


Textual data can come from various sources, both internal to a company (satisfaction questionnaires, claims, customer messages, company documentation, archives) and external (social media, review sites). By identifying strengths and weaknesses, the tool helps companies make strategic data-driven decisions and predict (and, in some cases, prevent) possible future situations.


The goal of, in fact, is to favor a process that determines concrete actions, such as an improvement intervention with respect to a specific theme.

CELI.dialog is a tool that leverages NLP’s proprietary technologies to help organizations understand customers’ requests and respond to their needs, creating personalized conversation experiences.


The tool consists of several modules: Natural Language Understanding which analyzes text and voice to extract meaning. Dialog Manager to manage the dialogue logics and guide the conversation. Natural Language Generation to generate the text or speech response. Customizable proprietary Back Office, to create and manage conversational assistants independently.


By extracting valuable information from the dialogue with customers and/or prospects, brands can: expand their market and implement marketing strategies; automate customer management processes and understanding complex information; orient towards certain products based on the flow of dialogue; improve the customer journey in all its phases, anticipating and/or solving the needs of the individual user.

Our research

From local programs to international projects

Since 1999, CELI has been carrying out research and innovation projects in collaboration with universities (including the University of Turin, the Polytechnic of Turin, the University of Pisa, the Scuola Normale Superiore of Pisa, the University of Trento), research centers (Bruno Kessler Foundation, LINKS Foundation, Italian Institute of Technology (IIT)), European and non-European companies, scientific associations and the ICT sector (AI * IA: Italian Association for Artificial Intelligence; AILC: Italian Association of Computational Linguistics; AIUCD: Association for Digital Humanities and Digital Culture; ICT Innovation Hub — Piedmont Region), and publishes scientific articles on the results of these activities.

The activity is developed on three main lines: didactic activity, including agreements for training and advanced training internships; scientific activity through study projects on specific topics; participation in research projects co-financed both by the European Union (including the European Framework Programs Horizon 2014-2020 and Horizon Europe 2021-2027) and by national institutions (in particular projects of the Ministry of Innovation, University and Research) and local (POR-FESR projects).

Recent projects



Citizen curation of cultural activities



SPICE (Social cohesion, Participation, and Inclusion through Cultural Engagement) aims to encourage inclusive and collaborative participation in cultural activities by groups at risk of exclusion, encouraging them to give their own interpretation of cultural objects. The project involves the use of multilingual NLP technologies for the analysis and enrichment of textual content produced by citizens during curatorial activities.



Anonymization and pseudoanonymization of personal data

Development of an automatic anonymization service that allows companies to protect the personal data of their users contained in large collections of unstructured documents in natural language, in compliance with European and international regulations and standards (such as GDPR). The solution involves the use of Deep Learning algorithms and Natural Language Processing technologies.



Chatbots and voice assistants for healthcare


CANP “La Casa Nel Parco”, proposes solutions for e-health as the application of ICT technologies in the management of health processes, in telemedicine and telemonitoring, in order to support the accessibility and interoperability of information and health services, decentralization of care and improvement of care pathways.



Virtual assistants for patient assistance

The RiMotivAzione project has made it possible to develop a virtual assistant that increases the independence of patients by allowing them to carry out rehabilitation remotely and to receive correct monitoring within a complete and cutting-edge platform that integrates various technologies and thanks to the guidance of a voice assistant.



Social media monitoring for the management of natural disasters


The project aimed at developing a European platform which, through the use of multilingual semantic technologies, integrates emergency management data from multiple sources (including those provided by citizens through social media and crowdsourcing), to manage in time or prevent natural disasters.



Artificial Intelligence for the analysis of public health contracts


The project, carried out in partnership with Synapta, aims to create a Business Intelligence platform through Big Data technologies to transform public contracts in the health sector in actionable knowledge in business decisions. For the analysis of unstructured data, NLP techniques were used for the recognition of entities and extraction of relationships, tools for carrying out cross-database investigations and Linked Data technologies.

Last publications



De Marchi, Fabiola, Marcella Serioli, Alessandro Collo, Evelyn Gisell Belotti, Francesca Alloatti, Giampaolo Biroli, Andrea Bolioli, Roberto Cantello, Sergio Riso, and Letizia Mazzini. 2022. “A Telehealth Intervention for Nutritional Counseling in Amyotrophic Lateral Sclerosis Patients” Journal of Clinical Medicine 11, no. 15: 4286.


Andrea Bolioli, “Parlare con gli oggetti: tecnologia e filosofia delle interfacce vocali” in “Musica, Scienza e Linguaggio. Dall’acustica musicale agli assistenti vocali.” A cura di Sergio Giudici. Edizioni ETS (2022).






Alloatti, Francesca, Riccardo Tasso, Andrea Bolioli, Elena Messina, Daria Cantu, Elena Guidorzi, Chiara Agamennone, Enrico Brunetti, and Renata Marinello. “Can You Help Me Measure My Blood Sugar?” Co-design of a Voice Interface to Assist Patients and Caregivers at Home.” In 2021 IEEE Symposium on Computers and Communications (ISCC), pp. 1-4. IEEE, 2021.


Diaz-Agudo, Belen, Alessio Bosca, Andrea Bolioli, Guilermo Jimenez Jimenez Diaz, Tsvi Kuflik, and Alan J. Wecker. “Towards Personalized Social Recommendations for Cultural Heritage Activities: Methods and technology to enable cohesive and inclusive recommendations.” In Adjunct Proceedings of the 29th ACM Conference on User Modeling, Adaptation and Personalization, pp. 199-202. 2021.


Andrea Bolioli, Alessio Bosca, Anna Maria Marras, Rossana Damiano, and Antonio Lieto. ‘Citizen curation and NLP technologies for museums in the SPICE Project.’. In Book of Abstracts of AIUCD 2021: DHs for Society: e-quality, participation, rights and values in the Digital Age. Pisa, Italy, 2021


Andrea Bolioli, Nicola Benvenuti, Pietro Vigorelli, “ApproccioCapacitante® e studio computazionale dei cambiamenti nel lessico delle persone con demenza”. Atti del 21° Congresso Nazionale AIP La psicogeriatria: scienza della complessità (15-17 aprile 2021).


Francesca Alloatti, Luigi Di Caro e Alessio Bosca, “Conversation Analysis, Repair Sequences and Human Computer Interaction – A theoretical framework and an empirical proposal of action”, Deep Dial 2021


Viviana Patti, Valerio Basile, Cristina Bosco, Rossella Varvara, Michael Fell, Andrea Bolioli and Alessio Bosca, “EVALITA4ELG: Italian Benchmark Linguistic Resources, NLP Services and Tools for the ELG Platform”, IJCoL, 6-2 | -1, 105-129.



Ilaria Angela Amantea, Emilio Sulis, Guido Boella, Fabiola De Marchi, Letizia Mazzini, Francesca Alloatti and Andrea Bolioli. Adopting technologies for healthcare optimization: a chatbot for patient with Amyotrophic lateral sclerosis. ForItAAL 2020


De Francesco, Nazareno (2020). GUL.LE.VER @ GhigliottinAI: A Glove based Artificial Player to Solve the Language Game “La Ghigliottina”, Valerio Basile, Danilo Croce, Maria Di Maro, and Lucia C. Passaro, editors, Proceedings of the 7th evaluation campaign of Natural Language Processing and Speech tools for Italian (EVALITA 2020), Online.


Tarasconi, Francesco & Botros, Milad & Caserio, Matteo & Sportelli, Gianpiero & Giacalone, Giuseppe & Uttini, Carlotta & Vignati, Luca & Zanetta, Fabrizio. (2020). Natural Language Processing Applications in Case-Law Text Publishing. 10.3233/FAIA200859


Andrea Bolioli, Alessio Bosca, Nicola Benvenuti, Alessandro Mazzei, Pietro Vigorelli, “The Corpus Anchise 320 and the analysis of conversations between healthcare workers and people with dementia”. CLiC-it 2020, Proceedings of the Seventh Italian Conference on Computational Linguistics


Francesca Alloatti, Andrea Bolioli, Alessio Bosca, Mariafrancesca Guadalupi, “The RiMotivAzione Dialogue Corpus – Analysing Medical Discourse to Model a Digital Physiotherapist”, in Proceedings of LREC 2020 RaPID Workshop: Resources and Processing of Linguistic, Para-linguistic and Extra-linguistic Data from People with Various Forms of Cognitive/Psychiatric/Developmental Impairments


Andrea Bolioli, Nicola Benvenuti, Pietro Vigorelli, Alessandro Mazzei, “Analisi linguistica computazionale del Corpus Anchise di dialoghi operatore-paziente”, 65° Congresso Nazionale della Società Italiana di Gerontologia e Geriatria SIGG2020

Active PhDs

CELI periodically activates PhD programs in collaboration with the University of Turin and the Polytechnic of Turin, with the aims of carrying out research projects with an application in real contexts and of bonding the direct connection between the academic world and the labor market, through the inclusion of specialized figures.


At the moment CELI has activated the following PhD projects:

  • Human-Computer Interaction
    Department of Computer Science
    University of Turin
    Francesca Alloatti — Senior Computational Linguist
    The research project investigates how to improve conversational systems, how to better match them to human expectations and how to fix interactions that have gone wrong.
  • Development and application of Natural Language Understanding techniques for the enrichment of predictive models
    Department of Automation and Computer Science (DAUIN)
    Polytechnic of Turin
    Irene Benedetto — Associate Data Scientist
    The research project aims to develop and test innovative methodologies to create predictive models which, thanks to NLP technologies, exploit the large pool of data available to organizations and maximize their explanatory power for resolution of one or more specific business problems.

Language technologies are your passion and your field of study? Do you have a research idea that you can’t wait to develop? Let’s talk about it.

Share your proposal by sending an email to: