PhD: Constraint-Based Neural Language Models for Creative Language Generation

Descrizione

PhD: Constraint-Based Neural Language Models for Creative Language Generation Sintesi in italiano (traduzione automatica): L'organizzazione internazionale offre una posizione di dottorato nel progetto ERC TENACITY, focalizzato sulla generazione creativa del linguaggio attraverso modelli neurali. La sede è presso il Centre for Computational Linguistics. Il candidato ideale possiede una laurea magistrale in intelligenza artificiale, linguistica computazionale, informatica o un'educazione equivalente. Le mansioni principali includono lo sviluppo di metodi per integrare vincoli nei modelli di linguaggio basati su transformer e l'applicazione di tali metodi alla generazione creativa del linguaggio. È richiesta esperienza con reti neurali per l'elaborazione del linguaggio naturale, ottime competenze di programmazione (preferibilmente in Python e PyTorch) e una buona conoscenza dell'inglese. La posizione è a tempo pieno per un anno, con possibilità di estensione fino a quattro anni dopo una valutazione positiva. Creativity pervades human language use, yet the mechanisms behind it are poorly understood, and current language technology shows little true creativity. The ERC project TENACITY develops computational models of language that exhibit creativity, combining interpretable tensor factorization methods with neural language models. This PhD position focuses on the neural strand of the project. Neural language models are trained to reproduce the patterns of their training data, and thus show little genuine creativity in generation. By constraining a model’s generation process, it is incited to find novel ways of expressing the same content. The PhD research will develop methods for integrating constraints into transformer-based language models and apply them to creative language generation, informed by the latent semantic representations developed within the project. The precise focus will be determined in function of the candidate’s background and interests. You will join the TENACITY team of PhD researchers and postdocs at the Centre for Computational Linguistics. You hold a Master’s degree in artificial intelligence, computational linguistics, computer science, or equivalent education. You have a thorough experience with neural networks (deep learning) for natural language processing, and a good understanding of current (large) language model architectures. You have excellent programming skills (preferably Python and PyTorch). You have a keen interest in language and linguistics, and in computational creativity. You exhibit excellent proficiency in English and good oral and written communication skills. We offer a full-time PhD position for 1 year, extendable to 4 years after initial positive evaluation. You will be able to conduct scientific research within a high-level research environment, leading to a doctoral degree. You will work within an ERC-funded project team, with access to ample computing infrastructure and funding for conference travel. You will have the opportunity to participate in international conferences, and benefit from academic training and workshops. For more information please contact Prof. dr. Tim Van de Cruys, mail: tim.vandecruys@kuleuven.be . Annuncio in inglese. Fonte: Euraxess (Commissione europea).